{"data":[{"id":"openai/gpt-6-luna","object":"model","created":1626777600,"model_id":"openai/gpt-6-luna","canonical_slug":"openai/gpt-6-luna","display_name":"OpenAI: GPT-6 Luna","description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.05,"min_completion_price":0.25,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"openai/flex","service_tier":"flex","endpoint_name":"gpt-6-luna","prompt_price":0.05,"completion_price":0.25,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-6-luna","prompt_price":0.075,"completion_price":0.375,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-6-luna","prompt_price":0.1,"completion_price":0.5,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai/priority","service_tier":"priority","endpoint_name":"gpt-6-luna","prompt_price":0.2,"completion_price":1,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-6-sol","object":"model","created":1626777600,"model_id":"openai/gpt-6-sol","canonical_slug":"openai/gpt-6-sol","display_name":"OpenAI: GPT-6 Sol","description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1,"min_completion_price":5,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"openai/flex","service_tier":"flex","endpoint_name":"gpt-6-sol","prompt_price":1,"completion_price":5,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-6-sol","prompt_price":1.5,"completion_price":7.5,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-6-sol","prompt_price":2,"completion_price":10,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai/priority","service_tier":"priority","endpoint_name":"gpt-6-sol","prompt_price":4,"completion_price":20,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"inclusionai/ling-2.6-1t","object":"model","created":1626777600,"model_id":"inclusionai/ling-2.6-1t","canonical_slug":"inclusionai/ling-2.6-1t","display_name":"inclusionAI: Ling-2.6-1T","description":"Ling-2.6-1T: A Trillion-Parameter Comprehensive Flagship Model for Complex Tasks. \nTailored for real–world, complex scenarios, this trillion–parameter model introduces targeted optimizations across inference efficiency, token overhead, and agentic capabilities, making it highly effective for coding and daily workflows.","model_family":"inclusionai","model_family_id":71,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.3,"min_completion_price":2.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"novita","service_tier":"standard","endpoint_name":"inclusionai/ling-2.6-1t","prompt_price":0.3,"completion_price":2.5,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"interfaze/interfaze-beta","object":"model","created":1626777600,"model_id":"interfaze/interfaze-beta","canonical_slug":"interfaze/interfaze-beta","display_name":"Interfaze: Interfaze Beta","description":"Interfaze is an AI model built on a new architecture that merges specialized DNN/CNN models with LLMs for developer tasks that require deterministic output and high consistency like OCR, scraping, classification, web search and more.","model_family":"interfaze","category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":32000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":1.5,"min_completion_price":3.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"interfaze","service_tier":"standard","endpoint_name":"interfaze-beta","prompt_price":1.5,"completion_price":3.5,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-3.1-flash-lite","object":"model","created":1626777600,"model_id":"google/gemini-3.1-flash-lite","canonical_slug":"google/gemini-3.1-flash-lite","display_name":"Google: Gemini 3.1 flash lite","description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic workflows, simple data extraction, and applications where responsiveness and API cost are the primary constraints.\n\nSupports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.","model_family":"Gemini","model_family_id":15,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65532,"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.09375,"min_completion_price":0.5625,"supported_endpoint_types":["gemini","openai"],"provider_count":4,"providers":[{"provider_slug":"google-vertex/flex","service_tier":"flex","endpoint_name":"gemini-3.1-flash-lite","prompt_price":0.09375,"completion_price":0.5625,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3.1-flash-lite","prompt_price":0.1875,"completion_price":1.125,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-3.1-flash-lite","prompt_price":0.25,"completion_price":1.5,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex/priority","service_tier":"priority","endpoint_name":"gemini-3.1-flash-lite","prompt_price":0.3375,"completion_price":2.025,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.5-27b-bluestar-v3-derestricted","object":"model","created":1626777600,"model_id":"qwen/qwen3.5-27b-bluestar-v3-derestricted","canonical_slug":"qwen/qwen3.5-27b-bluestar-v3-derestricted","display_name":"Qwen: Qwen3.5 27B BlueStar v3 Derestricted","description":"Third-generation BlueStar finetune for creative roleplay, narrative prose, and multimodal Qwen3.5 27B workflows.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262100,"max_input_tokens":262100,"max_output_tokens":262100,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.31,"min_completion_price":0.31,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"nano-gpt","service_tier":"standard","endpoint_name":"Qwen3.5-27B-BlueStar-v3-Derestricted","prompt_price":0.31,"completion_price":0.31,"context_length":262100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"rednote-hilab/dots.ocr","object":"model","created":1626777600,"model_id":"rednote-hilab/dots.ocr","canonical_slug":"rednote-hilab/dots.ocr","display_name":"Rednote-Hilab: Dots.ocr","description":"dots.ocr is a powerful, multilingual document parser that unifies layout detection and content recognition within a single vision-language model while maintaining good reading order. Despite its compact 1.7B-parameter LLM foundation, it achieves state-of-the-art(SOTA) performance.","model_family":"dots.ocr","model_family_id":65,"category_type":"LLM","context_length":131070,"max_input_tokens":131070,"max_output_tokens":131070,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.01,"min_completion_price":0.0109,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"chutes","service_tier":"standard","endpoint_name":"rednote-hilab/dots.ocr","prompt_price":0.01,"completion_price":0.0109,"context_length":131070,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"}]},{"id":"x-ai/grok-4.3","object":"model","created":1626777600,"model_id":"x-ai/grok-4.3","canonical_slug":"x-ai/grok-4.3","display_name":"xAI: Grok 4.3","description":"Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning is always active and cannot be disabled or configured by effort level.\n\nIt supports a 1 million token context window with no output token limit, making it well-suited for long-document analysis, deep research, and multi-step agentic tasks. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.","model_family":"Grok","model_family_id":20,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":1000000,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":1,"min_completion_price":2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-4.3","prompt_price":1,"completion_price":2,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.6-flash","object":"model","created":1626777600,"model_id":"qwen/qwen3.6-flash","canonical_slug":"qwen/qwen3.6-flash","display_name":"Qwen: Qwen 3.6 Flash","description":"The Qwen3.6 native vision-language Flash model series delivers a significant performance boost over the 3.5-Flash version. This model particularly excels in agentic coding capabilities, substantially outperforming its predecessor on multiple code-agent benchmarks, as well as in mathematical and code reasoning. In terms of vision, it features markedly improved spatial intelligence, with especially notable enhancements in object localization and object detection.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.0825,"min_completion_price":0.495,"supported_endpoint_types":["openai"],"provider_count":6,"providers":[{"provider_slug":"alibaba/cn","service_tier":"flex","endpoint_name":"qwen3.6-flash","prompt_price":0.0825,"completion_price":0.495,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"qwen3.6-flash","prompt_price":0.0825,"completion_price":0.495,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/hk","service_tier":"standard","endpoint_name":"qwen3.6-flash","prompt_price":0.0825,"completion_price":0.495,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"qwen3.6-flash","prompt_price":0.0825,"completion_price":0.495,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/jp","service_tier":"standard","endpoint_name":"qwen3.6-flash","prompt_price":0.0825,"completion_price":0.495,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.6-flash","prompt_price":0.125,"completion_price":0.75,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.5-pro","object":"model","created":1626777600,"model_id":"openai/gpt-5.5-pro","canonical_slug":"openai/gpt-5.5-pro","display_name":"OpenAI: GPT-5.5 Pro","description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, and is designed for long-horizon problem solving, agentic coding, and precise execution across multi-step workflows.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":30,"min_completion_price":180,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.5-pro-2026-04-23","prompt_price":30,"completion_price":180,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.5","object":"model","created":1626777600,"model_id":"openai/gpt-5.5","canonical_slug":"openai/gpt-5.5","display_name":"OpenAI: GPT-5.5","description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":2.5,"min_completion_price":15,"supported_endpoint_types":["openai"],"provider_count":3,"providers":[{"provider_slug":"openai/flex","service_tier":"flex","endpoint_name":"gpt-5.5-2026-04-23","prompt_price":2.5,"completion_price":15,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.5-2026-04-23","prompt_price":5,"completion_price":30,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai/priority","service_tier":"priority","endpoint_name":"gpt-5.5-2026-04-23","prompt_price":12.5,"completion_price":75,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-v4-pro","object":"model","created":1626777600,"model_id":"deepseek/deepseek-v4-pro","canonical_slug":"deepseek/deepseek-v4-pro","display_name":"DeepSeek: Deepseek V4 Pro","description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.","model_family":"DeepSeek","model_family_id":9,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.825,"min_completion_price":1.6505,"supported_endpoint_types":["openai"],"provider_count":6,"providers":[{"provider_slug":"alibaba/cn/flex","service_tier":"flex","endpoint_name":"deepseek-v4-pro","prompt_price":0.825,"completion_price":1.6505,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"deepseek-v4-pro","prompt_price":0.825,"completion_price":1.6505,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"deepseek-v4-pro","prompt_price":0.825,"completion_price":1.6505,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/jp","service_tier":"standard","endpoint_name":"deepseek-v4-pro","prompt_price":0.825,"completion_price":1.6505,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"deepseek-v4-pro","prompt_price":1.2,"completion_price":2.4,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"baidu-cloud","service_tier":"flex","endpoint_name":"deepseek-v4-pro","prompt_price":1.69,"completion_price":3.38,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"deepseek/deepseek-v4-flash","object":"model","created":1626777600,"model_id":"deepseek/deepseek-v4-flash","canonical_slug":"deepseek/deepseek-v4-flash","display_name":"DeepSeek: Deepseek V4 Flash","description":"284B total / 13B active params. Your fast, efficient, and economical choice.","model_family":"DeepSeek","model_family_id":9,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.056,"min_completion_price":0.112,"supported_endpoint_types":["openai"],"provider_count":7,"providers":[{"provider_slug":"baidu-cloud","service_tier":"flex","endpoint_name":"deepseek-v4-flash","prompt_price":0.056,"completion_price":0.112,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"alibaba/cn/flex","service_tier":"flex","endpoint_name":"deepseek-v4-flash","prompt_price":0.069,"completion_price":0.1375,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"deepseek-v4-flash","prompt_price":0.069,"completion_price":0.1375,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"deepseek-v4-flash","prompt_price":0.069,"completion_price":0.1375,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"},{"provider_slug":"alibaba/jp","service_tier":"standard","endpoint_name":"deepseek-v4-flash","prompt_price":0.069,"completion_price":0.1375,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"deepseek-v4-flash","prompt_price":0.1,"completion_price":0.2,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"},{"provider_slug":"deepinfra","service_tier":"flex","endpoint_name":"deepseek-ai/DeepSeek-V4-Flash","prompt_price":0.14,"completion_price":0.28,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"}]},{"id":"qwen/qwen3.6-27b","object":"model","created":1626777600,"model_id":"qwen/qwen3.6-27b","canonical_slug":"qwen/qwen3.6-27b","display_name":"Qwen: Qwen3.6-27B","description":"The Qwen3.6 27B native vision-language dense model builds upon the 3.5-27B version, with key improvements in agentic coding capabilities and enhanced STEM reasoning and inference skills. In the vision modality, it demonstrates significant advances in spatial intelligence, object localization, and detection, while video understanding, document OCR, and visual agent capabilities continue to improve steadily.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":64000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.3,"min_completion_price":1.8,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.6-27b","prompt_price":0.3,"completion_price":1.8,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"chutes","service_tier":"standard","endpoint_name":"Qwen/Qwen3.6-27B-TEE","prompt_price":0.5,"completion_price":2,"context_length":262140,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"xiaomi/mimo-v2.5","object":"model","created":1626777600,"model_id":"xiaomi/mimo-v2.5","canonical_slug":"xiaomi/mimo-v2.5","display_name":"Xiaomi: Mimo v2.5","description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass, making it ideal for integration with agent frameworks where strong reasoning, rich perception, and cost efficiency all matter.","model_family":"Mimo","model_family_id":35,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131100,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.14,"min_completion_price":0.28,"supported_endpoint_types":["openai"],"provider_count":3,"providers":[{"provider_slug":"xiaomi","service_tier":"standard","endpoint_name":"mimo-v2.5","prompt_price":0.14,"completion_price":0.28,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"inferx","service_tier":"standard","endpoint_name":"mimo-v25","prompt_price":0.14,"completion_price":0.28,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"XiaomiMiMo/MiMo-V2.5","prompt_price":0.4,"completion_price":2,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"xiaomi/mimo-v2.5-pro","object":"model","created":1626777600,"model_id":"xiaomi/mimo-v2.5-pro","canonical_slug":"xiaomi/mimo-v2.5-pro","display_name":"Xiaomi: Mimo v2.5 Pro","description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro. It can independently and autonomously complete professional tasks that would take human experts days or weeks, involving more than a thousand tool calls. Its context length of up to 1M makes it well suited for integration with a wide range of agent frameworks.","model_family":"Mimo","model_family_id":35,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131100,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.435,"min_completion_price":0.87,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"gmicloud","service_tier":"standard","endpoint_name":"XiaomiMiMo/MiMo-V2.5-Pro","prompt_price":0.435,"completion_price":0.87,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"bf16"},{"provider_slug":"xiaomi","service_tier":"standard","endpoint_name":"mimo-v2.5-pro","prompt_price":1,"completion_price":3,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"inclusionai/ling-2.6-flash","object":"model","created":1626777600,"model_id":"inclusionai/ling-2.6-flash","canonical_slug":"inclusionai/ling-2.6-flash","display_name":"inclusionAI: Ling-2.6-flash","description":"Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency. It delivers performance comparable to state-of-the-art models at a similar scale while significantly reducing token usage across coding, document processing, and lightweight agent workflows.","model_family":"inclusionai","model_family_id":71,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"novita","service_tier":"standard","endpoint_name":"inclusionai/ling-2.6-flash","prompt_price":0.1,"completion_price":0.3,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"moonshotai/kimi-k2.6","object":"model","created":1626777600,"model_id":"moonshotai/kimi-k2.6","canonical_slug":"moonshotai/kimi-k2.6","display_name":"Moonshot: Kimi K2.6","description":"Kimi K2.6 is an open-source, native multimodal agentic model that significantly advances practical capabilities in long-horizon coding, coding-driven design, and swarm-based task orchestration. It robustly executes complex, end-to-end development tasks across multiple programming languages and domains, seamlessly transforming simple prompts and visual inputs into production-ready, aesthetically precise interfaces and full-stack workflows. Uniquely engineered for high scalability, K2.6 can horizontally orchestrate up to 300 domain-specialized sub-agents through 4,000 coordinated steps, dynamically decomposing intricate tasks to deliver diverse end-to-end outputs—from documents and spreadsheets to fully functional websites—in a single autonomous run. Furthermore, its proactive execution capabilities empower persistent, 24/7 background agents to manage schedules, deploy code, and orchestrate cross-platform operations entirely without human oversight, establishing it as a premier foundational model for next-gener","model_family":"Kimi","model_family_id":27,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.44695,"min_completion_price":1.85655,"supported_endpoint_types":["openai"],"provider_count":6,"providers":[{"provider_slug":"alibaba/cn/flex","service_tier":"flex","endpoint_name":"kimi-k2.6","prompt_price":0.44695,"completion_price":1.85655,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"inceptron","service_tier":"standard","endpoint_name":"moonshotai/Kimi-K2.6","prompt_price":0.65,"completion_price":3.41,"context_length":256000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int4"},{"provider_slug":"siliconflow","service_tier":"standard","endpoint_name":"moonshotai/Kimi-K2.6","prompt_price":0.77,"completion_price":4,"context_length":262000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"moonshotai/kimi-k2.6","prompt_price":0.8,"completion_price":3.4,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"moonshotai","service_tier":"standard","endpoint_name":"kimi-k2.6","prompt_price":0.95,"completion_price":4,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int4"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"moonshotai/kimi-k2.6","prompt_price":0.95,"completion_price":4,"context_length":262140,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.6-max-preview","object":"model","created":1626777600,"model_id":"qwen/qwen3.6-max-preview","canonical_slug":"qwen/qwen3.6-max-preview","display_name":"Qwen: Qwen3.6 Max Preview","description":"The Max model, the largest and most capable variant in the Qwen3.6 series, is now available in a preview version. At present, only its plain-text capabilities are open for experimentation. Compared with the previously released Qwen3-Max and Qwen3.6-Plus, this model features enhanced vibe coding abilities, more efficient coding agent execution, and significantly improved front-end development skills. Additionally, its long-tail knowledge retention has been further upgraded.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":64000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.65,"min_completion_price":3.9,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.6-max-preview","prompt_price":0.65,"completion_price":3.9,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.6-35b-a3b","object":"model","created":1626777600,"model_id":"qwen/qwen3.6-35b-a3b","canonical_slug":"qwen/qwen3.6-35b-a3b","display_name":"Qwen: Qwen3.6-35B-A3B","description":"The Qwen3.6 35B-A3B native vision-language model is built on a hybrid architecture that integrates linear attention mechanisms with a sparse mixture-of-experts framework, achieving higher inference efficiency. Compared with the 3.5-35B-A3B, this model demonstrates significantly improved agentic coding capabilities, mathematical and code reasoning abilities, spatial intelligence, as well as object localization and object detection performance.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":64000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.124,"min_completion_price":0.7425,"supported_endpoint_types":["openai"],"provider_count":7,"providers":[{"provider_slug":"alibaba/cn","service_tier":"flex","endpoint_name":"qwen3.6-35b-a3b","prompt_price":0.124,"completion_price":0.7425,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"qwen3.6-35b-a3b","prompt_price":0.124,"completion_price":0.7425,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"qwen3.6-35b-a3b","prompt_price":0.124,"completion_price":0.7425,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3.6-35B-A3B","prompt_price":0.15,"completion_price":0.95,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"qwen/qwen3.6-35b-a3b","prompt_price":0.186,"completion_price":1.11375,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.6-35b-a3b","prompt_price":0.1875,"completion_price":1.125,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"siliconflow","service_tier":"standard","endpoint_name":"Qwen/Qwen3.6-35B-A3B","prompt_price":0.2,"completion_price":1.6,"context_length":262000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-opus-4.7","object":"model","created":1626777600,"model_id":"anthropic/claude-opus-4.7","canonical_slug":"anthropic/claude-opus-4.7","display_name":"Anthropic: Claude Opus 4.7","description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\n\nBeyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":5,"min_completion_price":25,"supported_endpoint_types":["anthropic","openai"],"provider_count":3,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-opus-4-7","prompt_price":5,"completion_price":25,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"amazon-bedrock/us","service_tier":"standard","endpoint_name":"global.anthropic.claude-opus-4-7","prompt_price":5,"completion_price":25,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-opus-4-7","prompt_price":5,"completion_price":25,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-5.1","object":"model","created":1626777600,"model_id":"z-ai/glm-5.1","canonical_slug":"z-ai/glm-5.1","display_name":"Z.AI: GLM 5.1","description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on a single task for more than 8 hours, autonomously planning, executing, and improving itself throughout the process, ultimately delivering complete, engineering-grade results.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":200000,"max_input_tokens":200000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.4125,"min_completion_price":1.6505,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"alibaba/cn","service_tier":"flex","endpoint_name":"glm-5.1","prompt_price":0.4125,"completion_price":1.6505,"context_length":202000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"glm-5.1","prompt_price":0.4125,"completion_price":1.6505,"context_length":202000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"glm-5.1","prompt_price":0.4125,"completion_price":1.6505,"context_length":202000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-5.1","prompt_price":1.4,"completion_price":4.4,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemma-4-26b-a4b","object":"model","created":1626777600,"model_id":"google/gemma-4-26b-a4b","canonical_slug":"google/gemma-4-26b-a4b","display_name":"Google: Gemma 4 26B A4B","description":"Gemma 4 26B A4B is built for developers who need scalable performance without sacrificing core capabilities.Crucially, it retains the massive 256K-token context window of the 31B model, making it highly competitive for long-context RAG and processing extensive, image-rich document datasets. It fully supports the series' core innovations: native Thinking mode for advanced logic, Interleaved Multimodal Input for dynamic text-image workflows, and flawless document/UI parsing. Equipped with native Function Calling and robust coding proficiencies, the 26B A4B is the ideal, cost-effective engine for powering real-world agentic workflows, visual automation, and global applications across its 140+ pre-trained languages.","model_family":"Gemma","model_family_id":16,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":131072,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.07,"min_completion_price":0.34,"supported_endpoint_types":["openai"],"provider_count":5,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"google/gemma-4-26B-A4B-it","prompt_price":0.07,"completion_price":0.34,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"siliconflow","service_tier":"standard","endpoint_name":"google/gemma-4-26B-A4B-it","prompt_price":0.12,"completion_price":0.4,"context_length":262000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"google/gemma-4-26b-a4b-it","prompt_price":0.13,"completion_price":0.4,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"},{"provider_slug":"parasail","service_tier":"standard","endpoint_name":"parasail-gemma-4-26b-a4b-it","prompt_price":0.13,"completion_price":0.4,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"nextbit","service_tier":"standard","endpoint_name":"gemma4:26b-a4b","prompt_price":0.14,"completion_price":0.4,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemma-4-31b-it","object":"model","created":1626777600,"model_id":"google/gemma-4-31b-it","canonical_slug":"google/gemma-4-31b-it","display_name":"Google: Gemma 4 31B","description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.","model_family":"Gemma","model_family_id":16,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":131072,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.09,"min_completion_price":0.34,"supported_endpoint_types":["openai"],"provider_count":6,"providers":[{"provider_slug":"deepinfra/turbo","service_tier":"standard","endpoint_name":"google/gemma-4-31B-it-turbo","prompt_price":0.09,"completion_price":0.34,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"},{"provider_slug":"chutes/turbo","service_tier":"standard","endpoint_name":"google/gemma-4-31B-turbo-TEE","prompt_price":0.13,"completion_price":0.38,"context_length":131070,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"google/gemma-4-31b-it","prompt_price":0.14,"completion_price":0.4,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"},{"provider_slug":"pearl","service_tier":"standard","endpoint_name":"google/gemma-4-31b-it","prompt_price":0.14,"completion_price":0.4,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"google/gemma-4-31B-it","prompt_price":0.2,"completion_price":0.4,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"deepinfra/ultra","service_tier":"standard","endpoint_name":"google/gemma-4-31B-it-Ultra","prompt_price":0.27,"completion_price":0.76,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"qwen/qwen3.6-plus","object":"model","created":1626777600,"model_id":"qwen/qwen3.6-plus","canonical_slug":"qwen/qwen3.6-plus","display_name":"Qwen: Qwen 3.6 Plus","description":"The Qwen 3.6 Native Vision-Language Series Plus models demonstrate exceptional performance comparable to today's cutting-edge models, marking a significant improvement in effectiveness compared to the 3.5 series. These models feature substantial enhancements across various capabilities, including coding skills—such as Agentic coding, front-end programming, and Vibe coding—as well as multimodal object recognition, OCR, and object localization.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.138,"min_completion_price":0.8255,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"qwen3.6-plus","prompt_price":0.138,"completion_price":0.8255,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"qwen3.6-plus","prompt_price":0.138,"completion_price":0.8255,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"qwen3.6-plus","prompt_price":0.138,"completion_price":0.8255,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.6-plus","prompt_price":0.25,"completion_price":1.5,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"x-ai/grok-4.2-non-reasoning","object":"model","created":1626777600,"model_id":"x-ai/grok-4.2-non-reasoning","canonical_slug":"x-ai/grok-4.2-non-reasoning","display_name":"xAI: Grok 4.2 Non Reasoning","description":"Grok 4.20 is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.","model_family":"Grok","model_family_id":20,"category_type":"LLM","context_length":2000000,"max_input_tokens":2000000,"max_output_tokens":2000000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":1,"min_completion_price":2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-4.20-0309-non-reasoning","prompt_price":1,"completion_price":2,"context_length":2000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"x-ai/grok-4.2-reasoning","object":"model","created":1626777600,"model_id":"x-ai/grok-4.2-reasoning","canonical_slug":"x-ai/grok-4.2-reasoning","display_name":"xAI: Grok 4.2 Reasoning","description":"Grok 4.20 is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.","model_family":"Grok","model_family_id":20,"category_type":"LLM","context_length":2000000,"max_input_tokens":2000000,"max_output_tokens":2000000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":1,"min_completion_price":2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-4.20-0309-reasoning","prompt_price":1,"completion_price":2,"context_length":2000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"arcee-ai/trinity-large-thinking","object":"model","created":1626777600,"model_id":"arcee-ai/trinity-large-thinking","canonical_slug":"arcee-ai/trinity-large-thinking","display_name":"Arcee AI: Trinity Large Thinking","description":"Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks.","model_family":"Trinity","model_family_id":84,"category_type":"LLM","context_length":262100,"max_input_tokens":262100,"max_output_tokens":80000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.25,"min_completion_price":0.9,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"arcee-ai","service_tier":"standard","endpoint_name":"trinity-large-thinking","prompt_price":0.25,"completion_price":0.9,"context_length":262100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-5v-turbo","object":"model","created":1626777600,"model_id":"z-ai/glm-5v-turbo","canonical_slug":"z-ai/glm-5v-turbo","display_name":"Z.AI: GLM 5V Turbo","description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding, and task execution, and works seamlessly with agents to complete the full loop of “perceive → plan → execute“.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":202800,"max_input_tokens":202800,"max_output_tokens":131100,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.79,"min_completion_price":3.44,"supported_endpoint_types":["openai"],"provider_count":5,"providers":[{"provider_slug":"bigmodel","service_tier":"standard","endpoint_name":"glm-5v-turbo","prompt_price":0.79,"completion_price":3.44,"context_length":202800,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-5v-turbo","prompt_price":1.2,"completion_price":4,"context_length":202800,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"zai-org/glm-5v-turbo","prompt_price":1.2,"completion_price":4,"context_length":204800,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"zai-org/glm-5v-turbo","prompt_price":1.2,"completion_price":4,"context_length":202750,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"siliconflow","service_tier":"standard","endpoint_name":"zai-org/GLM-5V-Turbo","prompt_price":1.2,"completion_price":4,"context_length":205000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"kwaipilot/kat-coder-pro-v2","object":"model","created":1626777600,"model_id":"kwaipilot/kat-coder-pro-v2","canonical_slug":"kwaipilot/kat-coder-pro-v2","display_name":"Kwaipilot: KAT-Coder-Pro V2","description":"KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions, with a focus on large-scale production environments, multi-system coordination, and seamless integration across modern software stacks, while also supporting web aesthetics generation to produce production-grade landing pages and presentation decks.","model_family":"Kwaipilot","model_family_id":73,"category_type":"LLM","context_length":262140,"max_input_tokens":262140,"max_output_tokens":144000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.3,"min_completion_price":1.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"kwaipilot/kat-coder-pro-v2","prompt_price":0.3,"completion_price":1.2,"context_length":262140,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seed-2.0-pro","object":"model","created":1626777600,"model_id":"bytedance/seed-2.0-pro","canonical_slug":"bytedance/seed-2.0-pro","display_name":"ByteDance: Seed 2.0 Pro","description":"Built for the Agent era, it delivers stable performance in complex reasoning and long-horizon tasks, including multi-step planning, visual-text reasoning, video understanding, and advanced analysis.","model_family":"Seed","model_family_id":51,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.5,"min_completion_price":3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260328083931-gmclv","prompt_price":0.5,"completion_price":3,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"minimax/minimax-m2.7","object":"model","created":1626777600,"model_id":"minimax/minimax-m2.7","canonical_slug":"minimax/minimax-m2.7","display_name":"MiniMax: MiniMax M2.7","description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.\n\nTrained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.","model_family":"MiniMax","model_family_id":36,"category_type":"LLM","context_length":204800,"max_input_tokens":204800,"max_output_tokens":131000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.25,"min_completion_price":1,"supported_endpoint_types":["openai"],"provider_count":7,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"MiniMaxAI/MiniMax-M2.7","prompt_price":0.25,"completion_price":1,"context_length":196608,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"minimax","service_tier":"standard","endpoint_name":"MiniMax-M2.7","prompt_price":0.3,"completion_price":1.2,"context_length":204800,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"minimax/minimax-m2.7","prompt_price":0.3,"completion_price":1.2,"context_length":204800,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"minimaxai/minimax-m2.7","prompt_price":0.3,"completion_price":1.2,"context_length":196608,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"together","service_tier":"standard","endpoint_name":"MiniMaxAI/MiniMax-M2.7","prompt_price":0.3,"completion_price":1.2,"context_length":196608,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"gmicloud","service_tier":"standard","endpoint_name":"MiniMaxAI/MiniMax-M2.7","prompt_price":0.3,"completion_price":1.2,"context_length":196608,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"minimax/highspeed","service_tier":"priority","endpoint_name":"MiniMax-M2.7-highspeed","prompt_price":0.6,"completion_price":2.4,"context_length":204800,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.4-nano","object":"model","created":1626777600,"model_id":"openai/gpt-5.4-nano","canonical_slug":"openai/gpt-5.4-nano","display_name":"OpenAI: GPT-5.4 Nano","description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.\n\nThe model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.15,"min_completion_price":0.9375,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5.4-nano","prompt_price":0.15,"completion_price":0.9375,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.4-nano-2026-03-17","prompt_price":0.2,"completion_price":1.25,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.4-mini","object":"model","created":1626777600,"model_id":"openai/gpt-5.4-mini","canonical_slug":"openai/gpt-5.4-mini","display_name":"OpenAI: GPT-5.4 Mini","description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.\n\nThe model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.375,"min_completion_price":2.25,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"openai/flex","service_tier":"flex","endpoint_name":"gpt-5.4-mini","prompt_price":0.375,"completion_price":2.25,"context_length":400000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5.4-mini","prompt_price":0.5625,"completion_price":3.375,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.4-mini-2026-03-17","prompt_price":0.75,"completion_price":4.5,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai/priority","service_tier":"priority","endpoint_name":"gpt-5.4-mini","prompt_price":1.5,"completion_price":9,"context_length":400000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"mistral/mistral-small-2603","object":"model","created":1626777600,"model_id":"mistral/mistral-small-2603","canonical_slug":"mistral/mistral-small-2603","display_name":"Mistral: Mistral Small 4","description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from Magistral, multimodal understanding from Pixtral, and agentic coding capabilities from Devstral, enabling one model to handle complex analysis, software development, and visual tasks within the same workflow.","model_family":"Mistral","model_family_id":37,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.15,"min_completion_price":0.6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mistral","service_tier":"standard","endpoint_name":"mistral-small-2603","prompt_price":0.15,"completion_price":0.6,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-oss-safeguard-20b","object":"model","created":1626777600,"model_id":"openai/gpt-oss-safeguard-20b","canonical_slug":"openai/gpt-oss-safeguard-20b","display_name":"OpenAI: Gpt oss safeguard 20b","description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust \u0026 safety labeling.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":65536,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.075,"min_completion_price":0.3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"groq","service_tier":"standard","endpoint_name":"openai/gpt-oss-safeguard-20b","prompt_price":0.075,"completion_price":0.3,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"z-ai/glm-5-turbo","object":"model","created":1626777600,"model_id":"z-ai/glm-5-turbo","canonical_slug":"z-ai/glm-5-turbo","display_name":"Z.AI: GLM 5 Turbo","description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows involving long execution chains, with improved complex instruction decomposition, tool use, scheduled and persistent execution, and overall stability across extended tasks.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":202752,"max_input_tokens":202752,"max_output_tokens":131100,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.79,"min_completion_price":3.44,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"bigmodel","service_tier":"standard","endpoint_name":"glm-5-turbo","prompt_price":0.79,"completion_price":3.44,"context_length":202805,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-5-turbo","prompt_price":1.2,"completion_price":4,"context_length":202752,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.5-9b","object":"model","created":1626777600,"model_id":"qwen/qwen3.5-9b","canonical_slug":"qwen/qwen3.5-9b","display_name":"Qwen: Qwen3.5-9B","description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design with early fusion of multimodal tokens, allowing the model to process and reason across text and images within the same context.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.04,"min_completion_price":0.15,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3.5-9B","prompt_price":0.04,"completion_price":0.15,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"},{"provider_slug":"together","service_tier":"standard","endpoint_name":"Qwen/Qwen3.5-9B","prompt_price":0.17,"completion_price":0.25,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"bytedance/seed-2.0-lite","object":"model","created":1626777600,"model_id":"bytedance/seed-2.0-lite","canonical_slug":"bytedance/seed-2.0-lite","display_name":"ByteDance: Seed 2.0 Lite","description":"ByteDance-Seed-2.0-lite is a balanced model designed for high-frequency enterprise workloads, optimizing for both capability and cost. Its overall performance surpasses the previous-generation ByteDance-Seed-1.8. It is well-suited for production tasks such as unstructured information processing, text content creation, search and recommendation, and data analysis. The model supports long-context processing, multi-source information fusion, multi-step instruction execution, and high-fidelity structured outputs—delivering stable quality while significantly reducing cost.","model_family":"Seed","model_family_id":51,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.25,"min_completion_price":2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260306185136-sbw2b","prompt_price":0.25,"completion_price":2,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.4","object":"model","created":1626777600,"model_id":"openai/gpt-5.4","canonical_slug":"openai/gpt-5.4","display_name":"OpenAI: GPT-5.4","description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\n\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":1.25,"min_completion_price":7.5,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"openai/flex","service_tier":"flex","endpoint_name":"gpt-5.4-2026-03-05","prompt_price":1.25,"completion_price":7.5,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5.4","prompt_price":1.875,"completion_price":11.25,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.4-2026-03-05","prompt_price":2.5,"completion_price":15,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai/priority","service_tier":"priority","endpoint_name":"gpt-5.4-2026-03-05","prompt_price":5,"completion_price":30,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-3.1-flash-lite-preview","object":"model","created":1626777600,"model_id":"google/gemini-3.1-flash-lite-preview","canonical_slug":"google/gemini-3.1-flash-lite-preview","display_name":"Google: Gemini 3.1 flash lite preview","description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across key capabilities. Improvements span audio input/ASR, RAG snippet ranking, translation, data extraction, and code completion. Supports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.","model_family":"Gemini","model_family_id":15,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65535,"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1875,"min_completion_price":1.125,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3.1-flash-lite-preview","prompt_price":0.1875,"completion_price":1.125,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-3.1-flash-lite-preview","prompt_price":0.25,"completion_price":1.5,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/tongyi-deepresearch-30b-a3b","object":"model","created":1626777600,"model_id":"qwen/tongyi-deepresearch-30b-a3b","canonical_slug":"qwen/tongyi-deepresearch-30b-a3b","display_name":"Qwen: Tongyi DeepResearch 30B A3B","description":"Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizon, deep information-seeking tasks and delivers state-of-the-art performance on benchmarks like Humanity's Last Exam, BrowserComp, BrowserComp-ZH, WebWalkerQA, GAIA, xbench-DeepSearch, and FRAMES. This makes it superior for complex agentic search, reasoning, and multi-step problem-solving compared to prior models.\n\nThe model includes a fully automated synthetic data pipeline for scalable pre-training, fine-tuning, and reinforcement learning. It uses large-scale continual pre-training on diverse agentic data to boost reasoning and stay fresh. It also features end-to-end on-policy RL with a customized Group Relative Policy Optimization, including token-level gradients and negative sample filtering for stable training. The model supports ReAct for core ability checks and an IterResearch-based 'Heavy' mode for max performance through test-time scaling. It's ideal for advanced research agents, tool use, and heavy inference workflows.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131100,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.09,"min_completion_price":0.45,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"Alibaba-NLP/Tongyi-DeepResearch-30B-A3B","prompt_price":0.09,"completion_price":0.45,"context_length":131070,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3-vl-235b-a22b-instruct","object":"model","created":1626777600,"model_id":"qwen/qwen3-vl-235b-a22b-instruct","canonical_slug":"qwen/qwen3-vl-235b-a22b-instruct","display_name":"Qwen: Qwen3 VL 235B A22B Instruct","description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table extraction, multilingual OCR). The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\n\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows—turning sketches or mockups into code and assisting with UI debugging—while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32800,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.2,"min_completion_price":0.88,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3-VL-235B-A22B-Instruct","prompt_price":0.2,"completion_price":0.88,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"Qwen/Qwen3-VL-235B-A22B-Instruct","prompt_price":0.3,"completion_price":1.5,"context_length":131070,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3-vl-235b-a22b-thinking","object":"model","created":1626777600,"model_id":"qwen/qwen3-vl-235b-a22b-thinking","canonical_slug":"qwen/qwen3-vl-235b-a22b-thinking","display_name":"Qwen: Qwen3 VL 235B A22B Thinking","description":"Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math. The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning.\n\nBeyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows, turning sketches or mockups into code and assisting with UI debugging, while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262100,"max_input_tokens":262100,"max_output_tokens":32800,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.5,"min_completion_price":2.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"qwen/qwen3-vl-235b-a22b-thinking","prompt_price":0.5,"completion_price":2.5,"context_length":128000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"inception/mercury-2","object":"model","created":1626777600,"model_id":"inception/mercury-2","canonical_slug":"inception/mercury-2","display_name":"Inception: Mercury 2","description":"Mercury 2 doesn't decode sequentially. It generates responses through parallel refinement, producing multiple tokens simultaneously and converging over a small number of steps. Less typewriter, more editor revising a full draft at once. The result: \u003e5x faster generation with a fundamentally different speed curve.\n\nThat speed advantage also changes the reasoning trade-off. Today, higher intelligence means more test-time compute — longer chains, more samples, more retries — bought at the direct expense of latency and cost. Diffusion-based reasoning gets you reasoning-grade quality inside real-time latency budgets.","model_family":"Mercury","model_family_id":34,"category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.25,"min_completion_price":0.75,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"inception","service_tier":"standard","endpoint_name":"mercury-2","prompt_price":0.25,"completion_price":0.75,"context_length":128000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3.5-397b-a17b","object":"model","created":1626777600,"model_id":"qwen/qwen3.5-397b-a17b","canonical_slug":"qwen/qwen3.5-397b-a17b","display_name":"Qwen: Qwen3.5-397B-A17B","description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":65500,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.086,"min_completion_price":0.516,"supported_endpoint_types":["openai"],"provider_count":10,"providers":[{"provider_slug":"alibaba/cn","service_tier":"flex","endpoint_name":"qwen3.5-397b-a17b","prompt_price":0.086,"completion_price":0.516,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"qwen3.5-397b-a17b","prompt_price":0.086,"completion_price":0.516,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"qwen3.5-397b-a17b","prompt_price":0.086,"completion_price":0.516,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.5-397b-a17b","prompt_price":0.3,"completion_price":1.8,"context_length":262100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3.5-397B-A17B","prompt_price":0.45,"completion_price":3,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"morph","service_tier":"standard","endpoint_name":"morph-qwen35-397b","prompt_price":0.478,"completion_price":3.5,"context_length":262100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"qwen/qwen3.5-397b-a17b","prompt_price":0.55,"completion_price":3.5,"context_length":262140,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"qwen/qwen3.5-397b-a17b","prompt_price":0.6,"completion_price":3.6,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"nebius","service_tier":"standard","endpoint_name":"Qwen/Qwen3.5-397B-A17B","prompt_price":0.6,"completion_price":3.6,"context_length":262000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"},{"provider_slug":"gmicloud","service_tier":"standard","endpoint_name":"Qwen/Qwen3.5-397B-A17B","prompt_price":0.6,"completion_price":3.6,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"qwen/qwen3.5-122b-a10b","object":"model","created":1626777600,"model_id":"qwen/qwen3.5-122b-a10b","canonical_slug":"qwen/qwen3.5-122b-a10b","display_name":"Qwen: Qwen3.5-122B-A10B","description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":65500,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.2,"min_completion_price":1.6,"supported_endpoint_types":["openai"],"provider_count":3,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.5-122b-a10b","prompt_price":0.2,"completion_price":1.6,"context_length":262100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3.5-122B-A10B","prompt_price":0.29,"completion_price":2.4,"context_length":16384,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"qwen/qwen3.5-122b-a10b","prompt_price":0.3,"completion_price":2.4,"context_length":262140,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3.5-35b-a3b","object":"model","created":1626777600,"model_id":"qwen/qwen3.5-35b-a3b","canonical_slug":"qwen/qwen3.5-35b-a3b","display_name":"Qwen: Qwen3.5-35B-A3B","description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":65500,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.0285,"min_completion_price":0.2295,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"qwen3.5-35b-a3b","prompt_price":0.0285,"completion_price":0.2295,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"qwen3.5-35b-a3b","prompt_price":0.0285,"completion_price":0.2295,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"qwen3.5-35b-a3b","prompt_price":0.0285,"completion_price":0.2295,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.5-35b-a3b","prompt_price":0.125,"completion_price":1,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.5-27b","object":"model","created":1626777600,"model_id":"qwen/qwen3.5-27b","canonical_slug":"qwen/qwen3.5-27b","display_name":"Qwen: Qwen3.5-27B","description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":65500,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.043,"min_completion_price":0.344,"supported_endpoint_types":["openai"],"provider_count":6,"providers":[{"provider_slug":"alibaba/cn","service_tier":"flex","endpoint_name":"qwen3.5-27b","prompt_price":0.043,"completion_price":0.344,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"qwen3.5-27b","prompt_price":0.043,"completion_price":0.344,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"qwen3.5-27b","prompt_price":0.043,"completion_price":0.344,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.5-27b","prompt_price":0.15,"completion_price":1.2,"context_length":262100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3.5-27B","prompt_price":0.26,"completion_price":2.6,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"qwen/qwen3.5-27b","prompt_price":0.27,"completion_price":2.16,"context_length":262140,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3.5-flash","object":"model","created":1626777600,"model_id":"qwen/qwen3.5-flash","canonical_slug":"qwen/qwen3.5-flash","display_name":"Qwen: Qwen 3.5 Flash","description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.","model_family":"Qwen","model_family_id":49,"model_version":"3.5 flash","category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":0.2,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.5-flash","prompt_price":0.05,"completion_price":0.2,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/hk","service_tier":"standard","endpoint_name":"qwen3.5-flash","prompt_price":0.05,"completion_price":0.2,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.3-codex","object":"model","created":1626777600,"model_id":"openai/gpt-5.3-codex","canonical_slug":"openai/gpt-5.3-codex","display_name":"OpenAI: Gpt 5.3 codex","description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results on SWE-Bench Pro and strong performance on Terminal-Bench 2.0 and OSWorld-Verified, reflecting improved multi-language coding, terminal proficiency, and real-world computer-use skills. The model is optimized for long-running, tool-using workflows and supports interactive steering during execution, making it suitable for complex development tasks, debugging, deployment, and iterative product work.\n\nBeyond coding, GPT-5.3-Codex performs strongly on structured knowledge-work benchmarks such as GDPval, supporting tasks like document drafting, spreadsheet analysis, slide creation, and operational research across domains. It is trained with enhanced cybersecurity awareness, including vulnerability identification capabilities, and deployed with additional safeguards for high-risk use cases. Compared to prior Codex models, it is more token-efficient and approximately 25% faster, targeting professional end-to-end workflows that span reasoning, execution, and computer interaction.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"1","category_type":"LLM","context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":1.3125,"min_completion_price":10.5,"supported_endpoint_types":["openai-response"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5.3-codex","prompt_price":1.3125,"completion_price":10.5,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.3-codex","prompt_price":1.75,"completion_price":14,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"bytedance/seed-2.0-mini","object":"model","created":1626777600,"model_id":"bytedance/seed-2.0-mini","canonical_slug":"bytedance/seed-2.0-mini","display_name":"ByteDance: Seed 2.0 Mini","description":"ByteDance-Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning_effort modes, and multimodal understanding, and is optimized for lightweight tasks where cost and speed take priority.","model_family":"Seed","model_family_id":51,"model_version":"2.0","category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.4,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260623090335-q6j64","prompt_price":0.1,"completion_price":0.4,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.5-plus","object":"model","created":1626777600,"model_id":"qwen/qwen3.5-plus","canonical_slug":"qwen/qwen3.5-plus","display_name":"Qwen: Qwen 3.5 Plus","description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.","model_family":"Qwen","model_family_id":49,"model_version":"3.5 plus","category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65536,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.0575,"min_completion_price":0.344,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"alibaba/cn","service_tier":"flex","endpoint_name":"qwen3.5-plus","prompt_price":0.0575,"completion_price":0.344,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"qwen3.5-plus","prompt_price":0.0575,"completion_price":0.344,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"qwen3.5-plus","prompt_price":0.0575,"completion_price":0.344,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.5-plus","prompt_price":0.2,"completion_price":1.2,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-3.1-pro-preview","object":"model","created":1626777600,"model_id":"google/gemini-3.1-pro-preview","canonical_slug":"google/gemini-3.1-pro-preview","display_name":"Google: Gemini 3.1 pro preview","description":"Gemini 3.1 Pro is designed to tackle the most challenging agentic problems with strong coding and state-of-the-art reasoning capabilities as well as complex multimodal understanding. Compared to Gemini 2.5 Pro, it improves significantly on complex instruction following and delivers outcomes with better output efficiency.\n\nGemini 3 family models are thinking models, capable of reasoning through their thoughts before responding, resulting in enhanced performance and improved accuracy.","model_family":"Gemini","model_family_id":15,"model_version":"3.1","category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.75,"min_completion_price":4.5,"supported_endpoint_types":["gemini","openai"],"provider_count":4,"providers":[{"provider_slug":"google-vertex/flex","service_tier":"flex","endpoint_name":"gemini-3.1-pro-preview","prompt_price":0.75,"completion_price":4.5,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3.1-pro-preview","prompt_price":1.5,"completion_price":9,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-3.1-pro-preview","prompt_price":2,"completion_price":12,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex/priority","service_tier":"priority","endpoint_name":"gemini-3.1-pro-preview","prompt_price":2.7,"completion_price":16.2,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-3-flash-preview","object":"model","created":1626777600,"model_id":"google/gemini-3-flash-preview","canonical_slug":"google/gemini-3-flash-preview","display_name":"Google: Gemini 3 flash preview","description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability.\n\nThe model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.","model_family":"Gemini","model_family_id":15,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65535,"input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1875,"min_completion_price":1.125,"supported_endpoint_types":["gemini","openai"],"provider_count":4,"providers":[{"provider_slug":"google-vertex/flex","service_tier":"flex","endpoint_name":"gemini-3-flash-preview","prompt_price":0.1875,"completion_price":1.125,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3-flash-preview","prompt_price":0.375,"completion_price":2.25,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-3-flash-preview","prompt_price":0.5,"completion_price":3,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex/priority","service_tier":"priority","endpoint_name":"gemini-3-flash-preview","prompt_price":0.675,"completion_price":4.05,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-opus-4.5","object":"model","created":1626777600,"model_id":"anthropic/claude-opus-4.5","canonical_slug":"anthropic/claude-opus-4.5","display_name":"Anthropic: Claude Opus 4.5","description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection. The model is designed to operate efficiently across varied effort levels, enabling developers to trade off speed, depth, and token usage depending on task requirements. It comes with a new parameter to control token efficiency, which can be accessed using the OpenRouter Verbosity parameter with low, medium, or high.\n\nOpus 4.5 supports advanced tool use, extended context management, and coordinated multi-agent setups, making it well-suited for autonomous research, debugging, multi-step planning, and spreadsheet/browser manipulation. It delivers substantial gains in structured reasoning, execution reliability, and alignment compared to prior Opus generations, while reducing token overhead and improving performance on long-running tasks.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":5,"min_completion_price":25,"supported_endpoint_types":["anthropic","openai"],"provider_count":2,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-opus-4-5-20251101-v1:0","prompt_price":5,"completion_price":25,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-opus-4-5-20251101","prompt_price":5,"completion_price":25,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-opus-4.6","object":"model","created":1626777600,"model_id":"anthropic/claude-opus-4.6","canonical_slug":"anthropic/claude-opus-4.6","display_name":"Anthropic: Claude Opus 4.6","description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective for large codebases, complex refactors, and multi-step debugging that unfolds over time. The model shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks than prior generations.\n\nBeyond coding, Opus 4.6 excels at sustained knowledge work. It produces near-production-ready documents, plans, and analyses in a single pass, and maintains coherence across very long outputs and extended sessions. This makes it a strong default for tasks that require persistence, judgment, and follow-through, such as technical design, migration planning, and end-to-end project execution.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":5,"min_completion_price":25,"supported_endpoint_types":["anthropic","openai"],"provider_count":3,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-opus-4-6-v1","prompt_price":5,"completion_price":25,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"amazon-bedrock/us","service_tier":"standard","endpoint_name":"global.anthropic.claude-opus-4-6","prompt_price":5,"completion_price":25,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-opus-4-6","prompt_price":5,"completion_price":25,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-4o-mini-tts/text-to-audio","object":"model","created":1626777600,"model_id":"openai/gpt-4o-mini-tts/text-to-audio","canonical_slug":"openai/gpt-4o-mini-tts/text-to-audio","display_name":"OpenAI: GPT-4o Mini TTS (Text to Audio)","description":"GPT-4o Mini TTS is OpenAI's cost-efficient text-to-speech model. It converts text input into natural-sounding audio output, supporting a variety of voices and tones.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"v1","category_type":"Text To Speech","context_length":10000,"max_input_tokens":10000,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["audio"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.6,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-4o-mini-tts","prompt_price":0.6,"completion_price":null,"context_length":10000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-4o-mini-transcribe/audio-to-text","object":"model","created":1626777600,"model_id":"openai/gpt-4o-mini-transcribe/audio-to-text","canonical_slug":"openai/gpt-4o-mini-transcribe/audio-to-text","display_name":"OpenAI: GPT-4o Mini Transcribe (Audio to Text)","description":"The gpt-4o-mini-transcribe model is a highly efficient speech-to-text solution designed to deliver accurate audio transcriptions while optimizing for speed and resource consumption. This model offers significant improvements in word error rate and language recognition, making it particularly effective in scenarios involving accents, noisy environments, and varying speech speeds. gpt-4o-mini-transcribe is ideal for applications that require quick and reliable transcription services.\n\ngpt-4o-mini-transcribe has been pretrained on specialized audio-centric datasets, which include diverse and high-quality audio samples, ensuring a deep understanding of speech nuances. This model supports a substantial context window of 16,000 tokens, allowing it to process longer audio inputs effectively. With a maximum output of 2,000 tokens, gpt-4o-mini-transcribe can generate detailed and comprehensive transcriptions. The training process incorporates rigorous enhancement techniques, including supervised fine-tuning and reinforcement learning, to optimize performance and accuracy.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"v1","category_type":"Speech To Text","context_length":10000,"max_input_tokens":10000,"max_output_tokens":10000,"input_modalities":["audio"],"output_modalities":["text"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.25,"min_completion_price":5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-4o-mini-transcribe","prompt_price":1.25,"completion_price":5,"context_length":10000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-4o-transcribe/audio-to-text","object":"model","created":1626777600,"model_id":"openai/gpt-4o-transcribe/audio-to-text","canonical_slug":"openai/gpt-4o-transcribe/audio-to-text","display_name":"OpenAI: GPT-4o Transcribee (Audio to Text)","description":"The gpt-4o-transcribe model is a cutting-edge speech-to-text solution that leverages the advanced capabilities of GPT-4o to deliver highly accurate audio transcriptions. This model offers significant improvements in word error rate and language recognition, surpassing the performance of previous models like Whisper. Designed for precision and efficiency, gpt-4o-transcribe aims to provide users with reliable and accurate transcripts, making it a valuable tool for various applications.\n\nGpt-4o-transcribe has been pretrained on specialized audio-centric datasets, which include diverse and high-quality audio samples, ensuring a deep understanding of speech nuances. This model supports a substantial context window of 16,000 tokens, allowing it to process longer audio inputs effectively. With a maximum output of 2,000 tokens, gpt-4o-transcribe can generate detailed and comprehensive transcriptions. The training process incorporates rigorous enhancement techniques, including supervised fine-tuning and reinforcement learning, to optimize performance and accuracy.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"v1","category_type":"Speech To Text","context_length":10000,"max_input_tokens":10000,"max_output_tokens":10000,"input_modalities":["audio"],"output_modalities":["text"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":2.5,"min_completion_price":10,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-4o-transcribe","prompt_price":2.5,"completion_price":10,"context_length":10000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-4o-mini","object":"model","created":1626777600,"model_id":"openai/gpt-4o-mini","canonical_slug":"openai/gpt-4o-mini","display_name":"OpenAI: Gpt 4o mini","description":"GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences common leaderboards","model_family":"OpenAI GPT","model_family_id":44,"model_version":"4o-mini","category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.15,"min_completion_price":0.6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-4o-mini-2024-07-18","prompt_price":0.15,"completion_price":0.6,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-4o","object":"model","created":1626777600,"model_id":"openai/gpt-4o","canonical_slug":"openai/gpt-4o","display_name":"OpenAI: Gpt 4o","description":"OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of GPT-4o in that it has additional RLHF. It is intended for research and evaluation.\n\nOpenAI notes that this model is not suited for production use-cases as it may be removed or redirected to another model in the future.\n\n\n","model_family":"OpenAI GPT","model_family_id":44,"model_version":"4o","category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16384,"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":1.875,"min_completion_price":7.5,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-4o","prompt_price":1.875,"completion_price":7.5,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-4o-2024-08-06","prompt_price":2.5,"completion_price":10,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-4.1-mini","object":"model","created":1626777600,"model_id":"openai/gpt-4.1-mini","canonical_slug":"openai/gpt-4.1-mini","display_name":"OpenAI: Gpt 4.1 mini","description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"4.1-mini","category_type":"LLM","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.3,"min_completion_price":1.2,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-4.1-mini","prompt_price":0.3,"completion_price":1.2,"context_length":1047576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-4.1-mini-2025-04-14","prompt_price":0.4,"completion_price":1.6,"context_length":1047576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-4.1","object":"model","created":1626777600,"model_id":"openai/gpt-4.1","canonical_slug":"openai/gpt-4.1","display_name":"OpenAI: Gpt 4.1","description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"4.1","category_type":"LLM","context_length":1047576,"max_input_tokens":1047576,"max_output_tokens":32768,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":2,"min_completion_price":8,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-4.1-2025-04-14","prompt_price":2,"completion_price":8,"context_length":1047576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-4","object":"model","created":1626777600,"model_id":"openai/gpt-4","canonical_slug":"openai/gpt-4","display_name":"OpenAI: Gpt 4","description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning capabilities. Training data: up to Sep 2021.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"4","category_type":"LLM","context_length":8191,"max_input_tokens":8191,"max_output_tokens":4096,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":22.5,"min_completion_price":45,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-4","prompt_price":22.5,"completion_price":45,"context_length":8191,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-4-0613","prompt_price":30,"completion_price":60,"context_length":8191,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-35-turbo","object":"model","created":1626777600,"model_id":"openai/gpt-35-turbo","canonical_slug":"openai/gpt-35-turbo","display_name":"OpenAI: Gpt 35 turbo","description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"3.5-turbo","category_type":"LLM","context_length":16385,"max_input_tokens":16385,"max_output_tokens":4096,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.5,"min_completion_price":1.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-3.5-turbo-0125","prompt_price":0.5,"completion_price":1.5,"context_length":16385,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.2","object":"model","created":1626777600,"model_id":"openai/gpt-5.2","canonical_slug":"openai/gpt-5.2","display_name":"OpenAI: Gpt 5.2","description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.\n\nBuilt for broad task coverage, GPT-5.2 delivers consistent gains across math, coding, sciende, and tool calling workloads, with more coherent long-form answers and improved tool-use reliability.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"5.2","category_type":"LLM","context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"input_modalities":["text","code","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":1.3125,"min_completion_price":10.5,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5.2","prompt_price":1.3125,"completion_price":10.5,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.2-2025-12-11","prompt_price":1.75,"completion_price":14,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-4.1-nano","object":"model","created":1626777600,"model_id":"openai/gpt-4.1-nano","canonical_slug":"openai/gpt-4.1-nano","display_name":"OpenAI: Gpt 4.1 nano","description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"4.1","category_type":"LLM","context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":33000,"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.075,"min_completion_price":0.3,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-4.1-nano","prompt_price":0.075,"completion_price":0.3,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-4.1-nano-2025-04-14","prompt_price":0.1,"completion_price":0.4,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5-nano","object":"model","created":1626777600,"model_id":"openai/gpt-5-nano","canonical_slug":"openai/gpt-5-nano","display_name":"OpenAI: Gpt 5 nano","description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"5","category_type":"LLM","context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.0375,"min_completion_price":0.3,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5-nano","prompt_price":0.0375,"completion_price":0.3,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5-nano-2025-08-07","prompt_price":0.05,"completion_price":0.4,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5-mini","object":"model","created":1626777600,"model_id":"openai/gpt-5-mini","canonical_slug":"openai/gpt-5-mini","display_name":"OpenAI: gpt 5 mini","description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"5","category_type":"LLM","context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1875,"min_completion_price":1.5,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5-mini","prompt_price":0.1875,"completion_price":1.5,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5-mini-2025-08-07","prompt_price":0.25,"completion_price":2,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-oss-20b","object":"model","created":1626777600,"model_id":"openai/gpt-oss-20b","canonical_slug":"openai/gpt-oss-20b","display_name":"OpenAI: Gpt oss 20b","description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"1","category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.03,"min_completion_price":0.14,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"openai/gpt-oss-20b","prompt_price":0.03,"completion_price":0.14,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"groq","service_tier":"standard","endpoint_name":"openai/gpt-oss-20b","prompt_price":0.075,"completion_price":0.3,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"openai/gpt-oss-120b","object":"model","created":1626777600,"model_id":"openai/gpt-oss-120b","canonical_slug":"openai/gpt-oss-120b","display_name":"OpenAI: gpt oss 120b","description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"1","category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.037,"min_completion_price":0.17,"supported_endpoint_types":["openai","gemini"],"provider_count":11,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"openai/gpt-oss-120b","prompt_price":0.037,"completion_price":0.17,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"crusoe","service_tier":"standard","endpoint_name":"openai/gpt-oss-120b","prompt_price":0.05,"completion_price":0.25,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"openai/gpt-oss-120b-maas","prompt_price":0.09,"completion_price":0.36,"context_length":131000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"gpt-oss-120b-250805","prompt_price":0.1,"completion_price":0.5,"context_length":131172,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"openai/gpt-oss-120b","prompt_price":0.1,"completion_price":0.2,"context_length":131070,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"digitalocean","service_tier":"standard","endpoint_name":"openai-gpt-oss-120b","prompt_price":0.1,"completion_price":0.7,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-oss-120b","prompt_price":0.1125,"completion_price":0.45,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"groq","service_tier":"standard","endpoint_name":"openai/gpt-oss-120b","prompt_price":0.15,"completion_price":0.6,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"nebius","service_tier":"standard","endpoint_name":"openai/gpt-oss-120b","prompt_price":0.15,"completion_price":0.6,"context_length":131100,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"},{"provider_slug":"databricks","service_tier":"standard","endpoint_name":"databricks-gpt-oss-120b","prompt_price":0.15,"completion_price":0.6,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"cerebras","service_tier":"standard","endpoint_name":"gpt-oss-120b","prompt_price":0.35,"completion_price":0.75,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"openai/gpt-5.1-codex-mini","object":"model","created":1626777600,"model_id":"openai/gpt-5.1-codex-mini","canonical_slug":"openai/gpt-5.1-codex-mini","display_name":"OpenAI: Gpt 5.1 codex mini","description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex\n\n","model_family":"OpenAI GPT","model_family_id":44,"model_version":"5","category_type":"LLM","context_length":400000,"max_input_tokens":400000,"max_output_tokens":100000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1875,"min_completion_price":1.5,"supported_endpoint_types":["openai-response"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5.1-codex-mini","prompt_price":0.1875,"completion_price":1.5,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.1-codex-mini","prompt_price":0.25,"completion_price":2,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5","object":"model","created":1626777600,"model_id":"openai/gpt-5","canonical_slug":"openai/gpt-5","display_name":"OpenAI: Gpt 5","description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"5","category_type":"LLM","context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9375,"min_completion_price":7.5,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5","prompt_price":0.9375,"completion_price":7.5,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5-2025-08-07","prompt_price":1.25,"completion_price":10,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5-codex","object":"model","created":1626777600,"model_id":"openai/gpt-5-codex","canonical_slug":"openai/gpt-5-codex","display_name":"OpenAI: Gpt 5 codex","description":"GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the reasoning.effort parameter\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"5","category_type":"LLM","context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9375,"min_completion_price":7.5,"supported_endpoint_types":["openai-response"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5-codex","prompt_price":0.9375,"completion_price":7.5,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5-codex","prompt_price":1.25,"completion_price":10,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.1","object":"model","created":1626777600,"model_id":"openai/gpt-5.1","canonical_slug":"openai/gpt-5.1","display_name":"OpenAI: Gpt 5.1","description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems.\n\nBuilt for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5","model_family":"OpenAI GPT","model_family_id":44,"model_version":"5","category_type":"LLM","context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9375,"min_completion_price":7.5,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5.1","prompt_price":0.9375,"completion_price":7.5,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.1-2025-11-13","prompt_price":1.25,"completion_price":10,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.1-codex","object":"model","created":1626777600,"model_id":"openai/gpt-5.1-codex","canonical_slug":"openai/gpt-5.1-codex","display_name":"OpenAI: Gpt 5.1 codex","description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the reasoning.effort parameter.\n\nCodex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"5","category_type":"LLM","context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9375,"min_completion_price":7.5,"supported_endpoint_types":["openai-response"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5.1-codex","prompt_price":0.9375,"completion_price":7.5,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.1-codex","prompt_price":1.25,"completion_price":10,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.1-chat","object":"model","created":1626777600,"model_id":"openai/gpt-5.1-chat","canonical_slug":"openai/gpt-5.1-chat","display_name":"OpenAI: Gpt 5.1 chat","description":"GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on harder queries, improving accuracy on math, coding, and multi-step tasks without slowing down typical conversations. The model is warmer and more conversational by default, with better instruction following and more stable short-form reasoning. GPT-5.1 Chat is designed for high-throughput, interactive workloads where responsiveness and consistency matter more than deep deliberation.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"5","category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":16400,"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9375,"min_completion_price":7.5,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5.1-chat","prompt_price":0.9375,"completion_price":7.5,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.1-chat-latest","prompt_price":1.25,"completion_price":10,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5-pro","object":"model","created":1626777600,"model_id":"openai/gpt-5-pro","canonical_slug":"openai/gpt-5-pro","display_name":"OpenAI: Gpt 5 pro","description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"5","category_type":"LLM","context_length":400000,"max_input_tokens":400000,"max_output_tokens":128000,"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":11.25,"min_completion_price":90,"supported_endpoint_types":["openai-response"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5-pro","prompt_price":11.25,"completion_price":90,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5-pro-2025-10-06","prompt_price":15,"completion_price":120,"context_length":400000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"tavily/tavily-search","object":"model","created":1626777600,"model_id":"tavily/tavily-search","canonical_slug":"tavily/tavily-search","display_name":"Tavily: Tavily Search","description":"Tavily is a search engine optimized for LLMs, aimed at efficient, quick and persistent search results. Unlike other search APIs such as Serp or Google, Tavily focuses on optimizing search for AI developers and autonomous AI agents. ","model_family":"Tavily","model_family_id":57,"category_type":"Search","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.008,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"tavily","service_tier":"standard","endpoint_name":"tavily-search","prompt_price":null,"completion_price":null,"request_price":0.008,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"tavily/tavily-extract","object":"model","created":1626777600,"model_id":"tavily/tavily-extract","canonical_slug":"tavily/tavily-extract","display_name":"Tavily: Tavily Extract","description":"Extract web page content from one or more specified URLs using Tavily Extract.","model_family":"Tavily","model_family_id":57,"category_type":"Extract","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.008,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"tavily","service_tier":"standard","endpoint_name":"tavily-extract","prompt_price":null,"completion_price":null,"request_price":0.008,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"google/veo3.1/text-to-video","object":"model","created":1626777600,"model_id":"google/veo3.1/text-to-video","canonical_slug":"google/veo3.1/text-to-video","display_name":"Google: Veo 3.1 (Text to Video)","description":"Google Veo 3.1 converts text prompts into videos with synchronized audio at native 1080p for high-quality outputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.","model_family":"Veo","model_family_id":59,"category_type":"Text to Video","input_modalities":["text"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.15,"supported_endpoint_types":["gemini","openai"],"provider_count":1,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"veo-3.1-generate-001","prompt_price":null,"completion_price":null,"request_price":0.15,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"wan/wan2.7/text-to-video","object":"model","created":1626777600,"model_id":"wan/wan2.7/text-to-video","canonical_slug":"wan/wan2.7/text-to-video","display_name":"Alibaba: Wan 2.7 (Text to Video)","description":"Generate high-quality images from text prompts using the WAN 2.7 model with advanced prompt understanding and detailed output.","model_family":"Wan","model_family_id":62,"category_type":"Text to Video","input_modalities":["text"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.05162,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"wan2.7-t2v","prompt_price":null,"completion_price":null,"request_price":0.05162,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/wan2.7/image-to-video","object":"model","created":1626777600,"model_id":"wan/wan2.7/image-to-video","canonical_slug":"wan/wan2.7/image-to-video","display_name":"Alibaba: Wan 2.7 (Image to Video)","description":"Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.","model_family":"Wan","model_family_id":62,"category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.05162,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"wan2.7-i2v","prompt_price":null,"completion_price":null,"request_price":0.05162,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/wan2.7/reference-to-video","object":"model","created":1626777600,"model_id":"wan/wan2.7/reference-to-video","canonical_slug":"wan/wan2.7/reference-to-video","display_name":"Alibaba: Wan 2.7 (Reference to Video)","description":"Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.","model_family":"Wan","model_family_id":62,"category_type":"Image to Video","input_modalities":["text","image","video"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.05162,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"wan2.7-r2v","prompt_price":null,"completion_price":null,"request_price":0.05162,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/wan2.7/video-edit","object":"model","created":1626777600,"model_id":"wan/wan2.7/video-edit","canonical_slug":"wan/wan2.7/video-edit","display_name":"Alibaba: Wan 2.7 (Video Edit)","description":"Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.","model_family":"Wan","model_family_id":62,"category_type":"Video to Video","input_modalities":["text","image","video"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.05162,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"wan2.7-videoedit","prompt_price":null,"completion_price":null,"request_price":0.05162,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"happyhorse/happyhorse1.0/text-to-video","object":"model","created":1626777600,"model_id":"happyhorse/happyhorse1.0/text-to-video","canonical_slug":"happyhorse/happyhorse1.0/text-to-video","display_name":"Alibaba: HappyHorse-1.0 (Text to Video)","description":"Generate 1080p video with synchronized native audio from a text prompt. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.","model_family":"HappyHorse","model_family_id":109,"category_type":"Text to Video","input_modalities":["text"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.07427,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"happyhorse-1.0-t2v","prompt_price":null,"completion_price":null,"request_price":0.07427,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"happyhorse/happyhorse1.0/image-to-video","object":"model","created":1626777600,"model_id":"happyhorse/happyhorse1.0/image-to-video","canonical_slug":"happyhorse/happyhorse1.0/image-to-video","display_name":"Alibaba: HappyHorse-1.0 (Image to Video)","description":"Alibaba's #1-ranked Happy Horse 1.0 — generate 1080p video with synchronized native audio and multilingual lip-sync from text prompts or images.","model_family":"HappyHorse","model_family_id":109,"category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.07427,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"happyhorse-1.0-i2v","prompt_price":null,"completion_price":null,"request_price":0.07427,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"happyhorse/happyhorse1.0/reference-to-video","object":"model","created":1626777600,"model_id":"happyhorse/happyhorse1.0/reference-to-video","canonical_slug":"happyhorse/happyhorse1.0/reference-to-video","display_name":"Alibaba: HappyHorse-1.0 (Reference to Video)","description":"Generate 1080p video with synchronized native audio from a text prompt and references. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.","model_family":"HappyHorse","model_family_id":109,"category_type":"Reference to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.07427,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"happyhorse-1.0-r2v","prompt_price":null,"completion_price":null,"request_price":0.07427,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"happyhorse/happyhorse1.0/video-edit","object":"model","created":1626777600,"model_id":"happyhorse/happyhorse1.0/video-edit","canonical_slug":"happyhorse/happyhorse1.0/video-edit","display_name":"Alibaba: HappyHorse-1.0 (Video Edit)","description":"HappyHorse video editing supports advanced video editing through natural language instructions. It allows for local or global editing of video elements using up to 5 reference images.","model_family":"HappyHorse","model_family_id":109,"category_type":"Video Edit","input_modalities":["text","image","video"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.07427,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"happyhorse-1.0-video-edit","prompt_price":null,"completion_price":null,"request_price":0.07427,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"happyhorse/happyhorse1.1/text-to-video","object":"model","created":1626777600,"model_id":"happyhorse/happyhorse1.1/text-to-video","canonical_slug":"happyhorse/happyhorse1.1/text-to-video","display_name":"Alibaba: HappyHorse-1.1 (Text to Video)","description":"Happy Horse 1.1 is Alibaba's #1-ranked video model. This text-to-video endpoint generates 1080p video with synchronized native audio and multilingual lip-sync from a text prompt alone.","model_family":"HappyHorse","model_family_id":109,"category_type":"Text to Video","input_modalities":["text"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.084,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"happyhorse-1.1-t2v","prompt_price":null,"completion_price":null,"request_price":0.084,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"happyhorse/happyhorse1.1/image-to-video","object":"model","created":1626777600,"model_id":"happyhorse/happyhorse1.1/image-to-video","canonical_slug":"happyhorse/happyhorse1.1/image-to-video","display_name":"Alibaba: HappyHorse-1.1 (Image to Video)","description":"Happy Horse 1.1 is Alibaba's #1-ranked video model. This image-to-video endpoint animates a still image into 1080p video with synchronized native audio and multilingual lip-sync","model_family":"HappyHorse","model_family_id":109,"category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.084,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"happyhorse-1.1-i2v","prompt_price":null,"completion_price":null,"request_price":0.084,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"happyhorse/happyhorse1.1/reference-to-video","object":"model","created":1626777600,"model_id":"happyhorse/happyhorse1.1/reference-to-video","canonical_slug":"happyhorse/happyhorse1.1/reference-to-video","display_name":"Alibaba: HappyHorse-1.1 (Reference to Video)","description":"Happy Horse 1.1 is Alibaba's #1-ranked video model. This reference-to-video endpoint turns up to 9 reference images into 1080p video with synchronized native audio and multilingual lip-sync for consistent characters.","model_family":"HappyHorse","model_family_id":109,"category_type":"Reference to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.084,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"happyhorse-1.1-r2v","prompt_price":null,"completion_price":null,"request_price":0.084,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/wan3.0/text-to-video","object":"model","created":1626777600,"model_id":"wan/wan3.0/text-to-video","canonical_slug":"wan/wan3.0/text-to-video","display_name":"Alibaba: Wan 3.0 (Text to Video)","description":"Wan 3.0 Text to Video generates cinematic videos from text prompts, with flexible 2-30 second duration, aspect ratio control, optional audio, and deep-thinking controls for high-quality video generation.","model_family":"Wan","model_family_id":62,"category_type":"Text to Video","input_modalities":["text"],"output_modalities":["video"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.03,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"wan3.0-video","prompt_price":null,"completion_price":null,"request_price":0.03,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/wan3.0/image-to-video","object":"model","created":1626777600,"model_id":"wan/wan3.0/image-to-video","canonical_slug":"wan/wan3.0/image-to-video","display_name":"Alibaba: Wan 3.0 (Image to Video)","description":"Wan 3.0 Image to Video animates a first-frame image into a cinematic video, with optional last-frame guidance, flexible 2-30 second duration, aspect ratio control, optional audio, and deep-thinking controls for high-quality motion and scene continuity.","model_family":"Wan","model_family_id":62,"category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.03,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"wan3.0-video","prompt_price":null,"completion_price":null,"request_price":0.03,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/wan3.0/reference-to-video","object":"model","created":1626777600,"model_id":"wan/wan3.0/reference-to-video","canonical_slug":"wan/wan3.0/reference-to-video","display_name":"Alibaba: Wan 3.0 (Reference to Video)","description":"Wan 3.0 Reference to Video creates coherent videos from prompts and multimodal references, including images, videos, and audio, with flexible 2-30 second duration and aspect ratio control for subject consistency, motion guidance, timing control, and scene continuity.","model_family":"Wan","model_family_id":62,"category_type":"Image to Video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.03,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"wan3.0-video","prompt_price":null,"completion_price":null,"request_price":0.03,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/wan3.0/video-edit","object":"model","created":1626777600,"model_id":"wan/wan3.0/video-edit","canonical_slug":"wan/wan3.0/video-edit","display_name":"Alibaba: Wan 3.0 (Video Edit)","description":"Wan 3.0 Reference to Video creates coherent videos from prompts and multimodal references, including images, videos, and audio, with flexible 2-30 second duration and aspect ratio control for subject consistency, motion guidance, timing control, and scene continuity.","model_family":"Wan","model_family_id":62,"category_type":"Video to Video","input_modalities":["text","image","video"],"output_modalities":["video"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.03,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"wan3.0-video","prompt_price":null,"completion_price":null,"request_price":0.03,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"google/transcoder/merge-videos","object":"model","created":1626777600,"model_id":"google/transcoder/merge-videos","canonical_slug":"google/transcoder/merge-videos","display_name":"Google Transcoder: Merge Videos","description":"Merge ordered video inputs into one MP4 with Google Cloud Transcoder.","model_family":"Google","model_family_id":18,"category_type":"Video to Video","input_modalities":["video"],"output_modalities":["video"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.00025,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"google-transcoder","service_tier":"standard","endpoint_name":"google/transcoder/merge-videos","prompt_price":null,"completion_price":null,"request_price":0.00025,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"minimax/minimax-h3/text-to-video","object":"model","created":1626777600,"model_id":"minimax/minimax-h3/text-to-video","canonical_slug":"minimax/minimax-h3/text-to-video","display_name":"MiniMax: H3 (Text to Video)","description":"MiniMax H3 is a frontier video model. This endpoint generates video from a text prompt alone, rendering at 2K in durations from 5 to 15 seconds across seven aspect ratios.","model_family":"MiniMax","model_family_id":36,"category_type":"Text to Video","input_modalities":["text"],"output_modalities":["video"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.08,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"minimax","service_tier":"standard","endpoint_name":"MiniMax-H3","prompt_price":null,"completion_price":null,"request_price":0.08,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"minimax/minimax-h3/image-to-video","object":"model","created":1626777600,"model_id":"minimax/minimax-h3/image-to-video","canonical_slug":"minimax/minimax-h3/image-to-video","display_name":"MiniMax: H3 (Image to Video)","description":"MiniMax H3 is a frontier video model. This endpoint animates a supplied image into 2K video, using it as the opening frame or pairs a first and last frame to control a transition between two images.","model_family":"MiniMax","model_family_id":36,"category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.08,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"minimax","service_tier":"standard","endpoint_name":"MiniMax-H3","prompt_price":null,"completion_price":null,"request_price":0.08,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"minimax/minimax-h3/reference-to-video","object":"model","created":1626777600,"model_id":"minimax/minimax-h3/reference-to-video","canonical_slug":"minimax/minimax-h3/reference-to-video","display_name":"MiniMax: H3 (Reference to Video)","description":"MiniMax H3 is a frontier video model. This endpoint generates 2K video from multimodal references up to 9 images for subject and style","model_family":"MiniMax","model_family_id":36,"category_type":"Image to Video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.08,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"minimax","service_tier":"standard","endpoint_name":"MiniMax-H3","prompt_price":null,"completion_price":null,"request_price":0.08,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"google/transcoder/merge-audio-video","object":"model","created":1626777600,"model_id":"google/transcoder/merge-audio-video","canonical_slug":"google/transcoder/merge-audio-video","display_name":"Google Transcoder: Merge Audio Video","description":"Merge videos with standalone audio files or audio from video files.","model_family":"Google","model_family_id":18,"category_type":"Video to Video","input_modalities":["video","audio"],"output_modalities":["audio"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.00025,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"google-transcoder","service_tier":"standard","endpoint_name":"google/transcoder/merge-audio-video","prompt_price":null,"completion_price":null,"request_price":0.00025,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"fireworks/ember-1","object":"model","created":1626777600,"model_id":"fireworks/ember-1","canonical_slug":"fireworks/ember-1","display_name":"Fireworks: Ember-1","description":"Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40% fewer tokens than the base model while maintaining comparable quality across Fireworks' evaluations. It is suited for coding, knowledge work, and agentic workflows where reasoning cost and latency matter.","model_family":"Ember","model_family_id":126,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":1048576,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"fireworks","service_tier":"standard","endpoint_name":"fireworks/ember-1","prompt_price":null,"completion_price":null,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"sao10k/l3.1-70b-hanami-x1","object":"model","created":1626777600,"model_id":"sao10k/l3.1-70b-hanami-x1","canonical_slug":"sao10k/l3.1-70b-hanami-x1","display_name":"Sao10k: l3.1-70b-hanami-x1","description":"## What is Llama 3.1 70B Hanami x1?\n\nLlama 3.1 70B Hanami x1 is a state-of-the-art large language model (LLM) developed by Sao10K, built upon Meta’s Llama 3.1 architecture with 70 billion parameters. Released on January 8, 2025, this model represents a significant advancement in multimodal AI capabilities, supporting both text and vision (image) inputs for sophisticated content generation, analysis, and reasoning tasks.\n\nThis model is specifically designed for developers and organizations requiring high-performance AI solutions that can process both textual and visual data simultaneously. With its extensive 16,000 token context window and OpenAI-compatible API, Llama 3.1 70B Hanami x1 offers seamless integration into existing workflows while delivering enhanced creativity, logical reasoning, and multimodal processing capabilities.\n\n**Key Value Proposition:** Llama 3.1 70B Hanami x1 bridges the gap between text-only and vision-capable AI models, offering enterprise-grade performance at competitive pricing ($3 per 1 million tokens) with support across multiple platforms including NeuroRouters, [Infron AI](https://infron.ai/), Featherless.ai, Ragwalla, and Ridvay.\n\n\n## How to Use Llama 3.1 70B Hanami x1\n\nGetting started with Llama 3.1 70B Hanami x1 is straightforward thanks to its OpenAI-compatible API structure. Follow these steps to integrate the model into your applications:\n\n1. **Choose Your Platform:** Select from available providers including NeuroRouters, [Infron AI](https://infron.ai/), Featherless.ai, Ragwalla, or Ridvay based on your specific requirements and subscription tier preferences (free, pro, or ultimate).\n2. **Obtain API Credentials:** Register for an account on your chosen platform and generate your API key from the dashboard. Most platforms offer free tier access for testing and evaluation purposes.\n3. **Configure API Endpoint:** Set up your API endpoint using the OpenAI-compatible format. The model identifier is typically `sao10k/l3.1-70b-hanami-x1` across platforms.\n4. **Prepare Your Input:** Format your requests to include both text prompts and optional image inputs. The model accepts standard text queries as well as base64-encoded images or image URLs for multimodal tasks.\n5. **Adjust Sampling Parameters:** Fine-tune output behavior using parameters such as temperature (0.0-2.0), top\\_p, top\\_k, frequency\\_penalty, presence\\_penalty, repetition\\_penalty, and min\\_p to achieve desired creativity and coherence levels.\n6. **Send Requests and Process Responses:** Submit your API requests and handle the streaming or complete responses. The model supports both synchronous and asynchronous processing modes.\n7. **Optimize for Your Use Case:** Leverage the 16,000 token context window for long-form content generation, complex reasoning tasks, or retrieval-augmented generation (RAG) applications requiring extensive context retention.\n\n**Pro Tip:** For vision tasks, ensure images are properly formatted and within size limits. The model performs best with clear, high-resolution images when processing visual information alongside text prompts.\n\n\n## Latest Insights and Research on Llama 3.1 70B Hanami x1\n\n### Multimodal Capabilities and Applications\n\nAccording to recent documentation from NeuroRouters, Llama 3.1 70B Hanami x1 is specifically engineered for multimodal tasks, supporting both text and vision inputs. This makes it particularly suitable for applications requiring simultaneous processing of textual and visual data, such as content creation platforms, advanced customer support systems with image analysis, and comprehensive data analysis workflows that integrate multiple data types.\n\n### Technical Specifications and Performance\n\nThe model features a substantial 16,000 token context window, as confirmed by multiple sources including [Infron AI](https://infron.ai/) and Featherless.ai. This extended context capacity enables the model to maintain coherence across long conversations, process extensive documents without losing contextual information, and handle complex multi-turn interactions that require reference to earlier parts of the conversation.\n\n#### 🎯 Parameter Count\n\n70 billion parameters for sophisticated reasoning and generation capabilities\n\n#### 🖼️ Vision Support\n\nNative image processing alongside text for true multimodal understanding\n\n#### 📊 Context Window\n\n16,000 tokens for handling extensive conversations and documents\n\n#### 🔌 API Compatibility\n\nOpenAI-compatible API for seamless integration with existing tools\n\n### Pricing and Accessibility\n\nBased on information from [Infron AI](https://infron.ai/) and Ridvay, the standard pricing model is set at $3 per 1 million input or output tokens. Multiple providers offer tiered subscription options:\n\n- **Free Tier:** Limited access for testing and evaluation purposes\n- **Pro Tier:** Enhanced rate limits and priority access\n- **Ultimate Tier:** Maximum throughput and dedicated support\n\nCompetitive Pricing: $3 per 1M tokens\n\n### Improvements Over Previous Models\n\nAccording to comparative analyses from Galaxy.ai and [Infron AI](https://infron.ai/), Llama 3.1 70B Hanami x1 represents a significant advancement over previous Sao10K models including Stheno v3.2 and Euryale v2.2. The improvements span three critical areas:\n\n- **Enhanced Creativity:** More nuanced and contextually appropriate content generation\n- **Improved Logical Reasoning:** Better performance on complex reasoning tasks and multi-step problem solving\n- **Advanced Multimodal Capabilities:** Superior integration of visual and textual information processing\n\n### RAG and Enterprise Applications\n\nRagwalla’s documentation highlights the model’s optimization for retrieval-augmented generation (RAG) applications. The extended context window and multimodal capabilities make it particularly effective for enterprise use cases requiring integration with knowledge bases, document repositories, and visual asset libraries.\n\n_Sources: NeuroRouters Setup Guide, [Infron AI](https://infron.ai/) API Documentation, Featherless.ai Model Specifications, Ragwalla RAG Integration Guide, Galaxy.ai Comparative Analysis_\n\n## Detailed Technical Specifications\n\n### Architecture and Model Design\n\nLlama 3.1 70B Hanami x1 is built on Meta’s Llama 3.1 architecture, incorporating 70 billion parameters distributed across multiple transformer layers. The model employs advanced attention mechanisms optimized for both text and vision processing, enabling seamless multimodal understanding and generation.\n\nThe architecture includes specialized vision encoders that process image inputs and integrate them with the text processing pipeline. This design allows the model to understand relationships between visual and textual information, making it capable of tasks such as image captioning, visual question answering, and multimodal content generation.\n\n### Context Window and Memory Management\n\nThe 16,000 token context window represents a significant advantage for applications requiring extensive context retention. This capacity translates to approximately 12,000-14,000 words of text, depending on tokenization, allowing the model to:\n\n- Process entire research papers or technical documents in a single context\n- Maintain conversation history across extended multi-turn dialogues\n- Integrate multiple source documents for comprehensive analysis\n- Support complex RAG workflows with extensive retrieved context\n\n### Sampling and Generation Parameters\n\nThe model supports comprehensive control over generation behavior through multiple parameters:\n\n#### Temperature\n\nControls randomness (0.0-2.0). Lower values produce more deterministic outputs, while higher values increase creativity and variation.\n\n#### Top-p (Nucleus Sampling)\n\nLimits token selection to cumulative probability mass. Values between 0.9-0.95 typically balance quality and diversity.\n\n#### Top-k\n\nRestricts selection to k most likely tokens. Useful for constraining output vocabulary in specific domains.\n\n#### Penalty Parameters\n\nFrequency, presence, and repetition penalties help reduce redundancy and encourage diverse expression.\n\n### Platform Availability and Integration\n\nLlama 3.1 70B Hanami x1 is accessible through multiple platforms, each offering unique features and integration options:\n\n- **NeuroRouters:** Specialized in vision and multimodal setups with comprehensive documentation\n- **[Infron AI](https://infron.ai/):** Unified API gateway with extensive model comparison tools\n- **Featherless.ai:** Focus on performance optimization and low-latency inference\n- **Ragwalla:** RAG-optimized infrastructure with built-in retrieval capabilities\n- **Ridvay:** Enterprise-focused platform with enhanced security and compliance features\n\n### Use Case Examples\n\nReal-world applications of Llama 3.1 70B Hanami x1 demonstrate its versatility:\n\n- **Content Creation:** Generate blog posts, articles, and marketing copy with accompanying image analysis for visual content recommendations\n- **Customer Support:** Process customer inquiries that include screenshots or product images alongside text descriptions\n- **Data Analysis:** Analyze charts, graphs, and visual data representations while generating textual insights and summaries\n- **Education:** Create interactive learning materials that combine textual explanations with visual diagrams and illustrations\n- **Research Assistance:** Process academic papers with figures and tables, generating comprehensive summaries and insights\n\n### Performance Optimization Tips\n\nTo maximize performance and cost-efficiency when using Llama 3.1 70B Hanami x1:\n\n1. Optimize prompt engineering to reduce unnecessary token usage while maintaining output quality\n2. Implement caching strategies for frequently used contexts to minimize redundant processing\n3. Use appropriate sampling parameters for your specific use case rather than default values\n4. Batch similar requests when possible to improve throughput\n5. Monitor token usage and adjust context window utilization based on actual requirements\n6. Leverage streaming responses for real-time applications to improve perceived latency","model_family":"Llama","model_family_id":31,"category_type":"LLM","context_length":10000,"max_input_tokens":10000,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":true,"supports_playground":true,"min_prompt_price":0,"min_completion_price":0,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"infermatic","service_tier":"standard","endpoint_name":"Sao10K-L3.1-70B-Hanami-x1","prompt_price":0,"completion_price":0,"context_length":32000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"}]},{"id":"deepseek/deepseek-v4-flash:free","object":"model","created":1626777600,"model_id":"deepseek/deepseek-v4-flash:free","canonical_slug":"deepseek/deepseek-v4-flash:free","display_name":"DeepSeek: Deepseek V4 Flash (Free)","description":"Infron offers free variants of selected models. Free variants carry the :free suffix (for example deepseek/deepseek-v4-flash:free) and are billed at $0.00 per token. Requests to free models never deduct from your credit balance. Learn more: https://infron.ai/docs/overview/free-models","model_family":"DeepSeek","model_family_id":9,"category_type":"LLM","context_length":1048580,"max_input_tokens":1048580,"max_output_tokens":65540,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0,"min_completion_price":0,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"infron/cn","service_tier":"standard","endpoint_name":"deepseek-v4-flash","prompt_price":0,"completion_price":0,"context_length":1048580,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"x-ai/grok-imagine-video-1.5/image-to-video","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-video-1.5/image-to-video","canonical_slug":"x-ai/grok-imagine-video-1.5/image-to-video","display_name":"xAI: Grok Imagine Video 1.5 (Image to Video)","description":"Generate videos from images with audio using xAI's Grok Imagine 1.5 Video model.","model_family":"Grok","model_family_id":20,"category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.14,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-video-1.5","prompt_price":0,"completion_price":0,"request_price":0.14,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"unknown"}]},{"id":"qwen/qwen3.8-27b:free","object":"model","created":1626777600,"model_id":"qwen/qwen3.8-27b:free","canonical_slug":"qwen/qwen3.8-27b:free","display_name":"Qwen: Qwen3.8 27B Uncensored (Free)","description":"Infron offers free variants of selected models. Free variants carry the :free suffix (for example deepseek/deepseek-v4-flash:free) and are billed at $0.00 per token. Requests to free models never deduct from your credit balance. Learn more: https://infron.ai/docs/overview/free-models","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"infron/us","service_tier":"standard","endpoint_name":"Qwen/Qwen3.8-27B","prompt_price":0,"completion_price":0,"context_length":204000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"deepseek/deepseek-v4-flash-0731:free","object":"model","created":1626777600,"model_id":"deepseek/deepseek-v4-flash-0731:free","canonical_slug":"deepseek/deepseek-v4-flash-0731:free","display_name":"DeepSeek: Deepseek V4 Flash 0731 (Free)","description":"Infron offers free variants of selected models. Free variants carry the :free suffix (for example deepseek/deepseek-v4-flash:free) and are billed at $0.00 per token. Requests to free models never deduct from your credit balance. Learn more: https://infron.ai/docs/overview/free-models","model_family":"DeepSeek","model_family_id":9,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"infron/cn","service_tier":"standard","endpoint_name":"deepseek-v4-flash-0731","prompt_price":0,"completion_price":0,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-v4.1-flash:free","object":"model","created":1626777600,"model_id":"deepseek/deepseek-v4.1-flash:free","canonical_slug":"deepseek/deepseek-v4.1-flash:free","display_name":"DeepSeek: Deepseek V4.1 Flash (Free)","description":"Infron offers free variants of selected models. Free variants carry the :free suffix (for example deepseek/deepseek-v4-flash:free) and are billed at $0.00 per token. Requests to free models never deduct from your credit balance. Learn more: https://infron.ai/docs/overview/free-models","model_family":"DeepSeek","model_family_id":9,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"infron/cn","service_tier":"standard","endpoint_name":"deepseek-v4.1-flash","prompt_price":0,"completion_price":0,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"chutes","service_tier":"standard","endpoint_name":"deepseek-v4.1-flash","prompt_price":0,"completion_price":0,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.8-27b-abliterated-cyber:free","object":"model","created":1626777600,"model_id":"qwen/qwen3.8-27b-abliterated-cyber:free","canonical_slug":"qwen/qwen3.8-27b-abliterated-cyber:free","display_name":"Qwen: Qwen3.8 27B Abliterated Cyber (Free)","description":"Infron offers free variants of selected models. Free variants carry the :free suffix (for example deepseek/deepseek-v4-flash:free) and are billed at $0.00 per token. Requests to free models never deduct from your credit balance. Learn more: https://infron.ai/docs/overview/free-models","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":131072,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"infron/us","service_tier":"standard","endpoint_name":"Qwen/Qwen3.8-27B-Abliterated-Cyber","prompt_price":0,"completion_price":0,"context_length":256000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"}]},{"id":"qwen/qwen3.8-flash:free","object":"model","created":1626777600,"model_id":"qwen/qwen3.8-flash:free","canonical_slug":"qwen/qwen3.8-flash:free","display_name":"Qwen: Qwen3.8 Flash (Free)","description":"Infron offers free variants of selected models. Free variants carry the :free suffix (for example deepseek/deepseek-v4-flash:free) and are billed at $0.00 per token. Requests to free models never deduct from your credit balance. Learn more: https://infron.ai/docs/overview/free-models","model_family":"Qwen","model_family_id":49,"category_type":"LLM","input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"infron/cn","service_tier":"standard","endpoint_name":"qwen3.8-flash","prompt_price":0,"completion_price":0,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"internlm/atria-dawn-preview:free","object":"model","created":1626777600,"model_id":"internlm/atria-dawn-preview:free","canonical_slug":"internlm/atria-dawn-preview:free","display_name":"Atria: Dawn Preview (Free)","description":"Atria Dawn Preview is an agentic language model developed by the Shanghai Artificial Intelligence Laboratory for scientific research and engineering. Its official model card describes a GLM-5.2-based mixture-of-experts foundation with 744 billion parameters. It is designed to sustain multi-step work: gathering evidence, planning experiments, writing and running code, inspecting results, and revising failed approaches using environmental feedback. The technical report describes a Verifiable Experience Pipeline that links tool interactions to executable environments and externally checked outcomes. Intended applications include deep research, software and machine-learning development, structured document delivery, and security analysis in authorized environments. These workflows require an external agent harness to execute tools and return observations. The hosted model accepts text input and produces text output, with a 256,000-token context window and a maximum generation limit of 65,536 tokens. It supports Chat Completions, Messages, and Responses interfaces. The release includes MIT-licensed model weights and a separate FP8 checkpoint; this does not establish the precision used by the hosted endpoint. As a preview model, its suitability should be checked against representative tasks; published benchmark results are developer-reported evaluations, not guarantees for individual deployments. Learn more at https://api.atria-asi.ai/docs.","model_family":"Atria","model_family_id":127,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":65536,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"atria","service_tier":"standard","endpoint_name":"Atria-Dawn-Preview","prompt_price":0,"completion_price":0,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"inclusionai/ling-3.1-flash:free","object":"model","created":1626777600,"model_id":"inclusionai/ling-3.1-flash:free","canonical_slug":"inclusionai/ling-3.1-flash:free","display_name":"Ling 3.1 Flash (Free)","description":"Ling 3.1 Flash is an inclusionAI hybrid reasoning model. Novita describes it as having 560B total parameters with 25B activated, and lists reasoning and function calling for text workloads. Although the catalog's model description mentions a 1M-token context, its structured hosted limits are 262,144 context tokens and 32,768 output tokens. This configuration uses those hosted limits; the broader model-level context claim is not treated as availability on this endpoint.","model_family":"inclusionai","model_family_id":71,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"novita","service_tier":"standard","endpoint_name":"inclusionai/ling-3.1-flash","prompt_price":0,"completion_price":0,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"apodex/apodex-1.1-mini:free","object":"model","created":1626777600,"model_id":"apodex/apodex-1.1-mini:free","canonical_slug":"apodex/apodex-1.1-mini:free","display_name":"Apodex 1.1 Mini (Free)","description":"Apodex 1.1 Mini is the 35B-parameter model in the Apodex 1.1 family, designed for agentic work in a smaller, locally deployable form. The family targets multi-step tasks involving reasoning and tool use; completing those tasks requires an external execution environment. Novita serves Mini as a text-input, text-output endpoint with a 262,144-token context and maximum output allowance, and lists reasoning, function calling, and structured outputs. These limits describe Novita's hosted endpoint, not measured performance.","model_family":"Apodex","model_family_id":119,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"novita","service_tier":"standard","endpoint_name":"apodex/apodex-1.1-mini","prompt_price":0,"completion_price":0,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"thenlper/gte-base","object":"model","created":1626777600,"model_id":"thenlper/gte-base","canonical_slug":"thenlper/gte-base","display_name":"Thenlper: Gte Base","description":"The gte-base embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, delivering efficient and effective semantic embeddings optimized for textual similarity, semantic search, and clustering applications.\n\n","model_family":"GTE","model_family_id":21,"category_type":"Embeddings","context_length":512,"max_input_tokens":512,"max_output_tokens":512,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.005,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"thenlper/gte-base","prompt_price":0.005,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"intfloat/e5-base-v2","object":"model","created":1626777600,"model_id":"intfloat/e5-base-v2","canonical_slug":"intfloat/e5-base-v2","display_name":"Intfloat: E5 Base V2","description":"The e5-base-v2 embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, similarity scoring, retrieval and clustering.\n\n","model_family":"E5","model_family_id":11,"category_type":"Embeddings","context_length":512,"max_input_tokens":512,"max_output_tokens":512,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.005,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"intfloat/e5-base-v2","prompt_price":0.005,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"sentence-transformers/paraphrase-minilm-l6-v2","object":"model","created":1626777600,"model_id":"sentence-transformers/paraphrase-minilm-l6-v2","canonical_slug":"sentence-transformers/paraphrase-minilm-l6-v2","display_name":"Sentence Transformers: Paraphrase Minilm L6 V2","description":"The paraphrase-MiniLM-L6-v2 embedding model converts sentences and short paragraphs into a 384-dimensional dense vector space, producing high-quality semantic embeddings optimized for paraphrase detection, semantic similarity scoring, clustering, and lightweight retrieval tasks.\n\n","model_family":"L6","model_family_id":30,"category_type":"Embeddings","context_length":512,"max_input_tokens":512,"max_output_tokens":512,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.005,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"sentence-transformers/paraphrase-MiniLM-L6-v2","prompt_price":0.005,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"sentence-transformers/all-minilm-l12-v2","object":"model","created":1626777600,"model_id":"sentence-transformers/all-minilm-l12-v2","canonical_slug":"sentence-transformers/all-minilm-l12-v2","display_name":"Sentence Transformers: All Minilm L12 V2","description":"The all-MiniLM-L12-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, clustering, and similarity-scoring.\n\n","model_family":"L12","model_family_id":29,"category_type":"Embeddings","context_length":512,"max_input_tokens":512,"max_output_tokens":512,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.005,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"sentence-transformers/all-MiniLM-L12-v2","prompt_price":0.005,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"baai/bge-base-en-v1.5","object":"model","created":1626777600,"model_id":"baai/bge-base-en-v1.5","canonical_slug":"baai/bge-base-en-v1.5","display_name":"BAAI: Bge Base En V1.5","description":"The bge-base-en-v1.5 embedding model converts English sentences and paragraphs into 768-dimensional dense vectors, delivering efficient, high-quality semantic embeddings optimized for retrieval, semantic search, and document-matching workflows. This version (v1.5) features improved similarity-score distribution and stronger retrieval performance out of the box.","model_family":"BGE","model_family_id":2,"category_type":"Embeddings","context_length":512,"max_input_tokens":512,"max_output_tokens":512,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.005,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"BAAI/bge-base-en-v1.5","prompt_price":0.005,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"sentence-transformers/multi-qa-mpnet-base-dot-v1","object":"model","created":1626777600,"model_id":"sentence-transformers/multi-qa-mpnet-base-dot-v1","canonical_slug":"sentence-transformers/multi-qa-mpnet-base-dot-v1","display_name":"Sentence Transformers: Multi Qa Mpnet Base Dot V1","description":"The multi-qa-mpnet-base-dot-v1 embedding model transforms sentences and short paragraphs into a 768-dimensional dense vector space, generating high-quality semantic embeddings optimized for question-and-answer retrieval, semantic search, and similarity-scoring across diverse content.","model_family":"Mpnet","model_family_id":38,"category_type":"Embeddings","context_length":512,"max_input_tokens":512,"max_output_tokens":512,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.005,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"sentence-transformers/multi-qa-mpnet-base-dot-v1","prompt_price":0.005,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"sentence-transformers/all-mpnet-base-v2","object":"model","created":1626777600,"model_id":"sentence-transformers/all-mpnet-base-v2","canonical_slug":"sentence-transformers/all-mpnet-base-v2","display_name":"Sentence Transformers: All Mpnet Base V2","description":"The all-mpnet-base-v2 embedding model encodes sentences and short paragraphs into a 768-dimensional dense vector space, providing high-fidelity semantic embeddings well suited for tasks like information retrieval, clustering, similarity scoring, and text ranking.","model_family":"Mpnet","model_family_id":38,"category_type":"Embeddings","context_length":512,"max_input_tokens":512,"max_output_tokens":512,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.005,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"sentence-transformers/all-mpnet-base-v2","prompt_price":0.005,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"sentence-transformers/all-minilm-l6-v2","object":"model","created":1626777600,"model_id":"sentence-transformers/all-minilm-l6-v2","canonical_slug":"sentence-transformers/all-minilm-l6-v2","display_name":"Sentence Transformers: All Minilm L6 V2","description":"The all-MiniLM-L6-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, enabling high-quality semantic representations that are ideal for downstream tasks such as information retrieval, clustering, similarity scoring, and text ranking.","model_family":"L6","model_family_id":30,"category_type":"Embeddings","context_length":512,"max_input_tokens":512,"max_output_tokens":512,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.005,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"sentence-transformers/all-MiniLM-L6-v2","prompt_price":0.005,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"exa/exa-search","object":"model","created":1626777600,"model_id":"exa/exa-search","canonical_slug":"exa/exa-search","display_name":"Exa: Exa Search","description":"By default, it automatically chooses the best search method using Exa’s embeddings-based model and other techniques to find the most relevant results for your query. You can also use Deep search for comprehensive results with query expansion and detailed context.","model_family":"Exa","model_family_id":12,"category_type":"Search","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.005,"min_completion_price":null,"min_request_price":0.005,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"exa","service_tier":"standard","endpoint_name":"exa-search","prompt_price":0.005,"completion_price":null,"request_price":0.005,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"openai/whisper-1/audio-to-text","object":"model","created":1626777600,"model_id":"openai/whisper-1/audio-to-text","canonical_slug":"openai/whisper-1/audio-to-text","display_name":"OpenAI: Whisper-1 (Audio to Text)","description":"The Whisper models are trained for speech recognition and translation tasks, capable of transcribing speech audio into the text in the language it is spoken (automatic speech recognition) as well as translated into English (speech translation). Researchers at OpenAI developed the models to study the robustness of speech processing systems trained under large-scale weak supervision. The model version 001 corresponds to whisper large v2.\n\nMax request data size: 25mb of audio can be converted from speech to text per API request.","model_family":"OpenAI","model_family_id":43,"category_type":"Speech To Text","context_length":10000,"max_input_tokens":10000,"max_output_tokens":10000,"input_modalities":["audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.006,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"whisper","prompt_price":0.006,"completion_price":null,"context_length":10000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"firecrawl/firecrawl-search","object":"model","created":1626777600,"model_id":"firecrawl/firecrawl-search","canonical_slug":"firecrawl/firecrawl-search","display_name":"firecrawl: Firecrawl Search","description":"Search the web and get full content from results\n\nFirecrawl’s search API allows you to perform web searches and optionally scrape the search results in one operation.","model_family":"Firecrawl","model_family_id":13,"model_version":"1","category_type":"Search","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.009,"min_completion_price":null,"min_request_price":0.009,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"firecrawl","service_tier":"standard","endpoint_name":"firecrawl-search","prompt_price":0.009,"completion_price":null,"request_price":0.009,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3-reranker-0.6b","object":"model","created":1626777600,"model_id":"qwen/qwen3-reranker-0.6b","canonical_slug":"qwen/qwen3-reranker-0.6b","display_name":"Qwen: Qwen3 Reranker 0.6B","description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B)","model_family":"Qwen","model_family_id":49,"model_version":"3","category_type":"Reranker","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.01,"min_completion_price":0.01,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3-Reranker-0.6B","prompt_price":0.01,"completion_price":0.01,"context_length":400,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"thenlper/gte-large","object":"model","created":1626777600,"model_id":"thenlper/gte-large","canonical_slug":"thenlper/gte-large","display_name":"Thenlper: Gte Large","description":"The gte-large embedding model converts English sentences, paragraphs and moderate-length documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for information retrieval, semantic textual similarity, reranking and clustering tasks. Trained via multi-stage contrastive learning on a large domain-diverse relevance corpus, it offers excellent performance across general-purpose embedding use-cases.","model_family":"GTE","model_family_id":21,"category_type":"Embeddings","context_length":512,"max_input_tokens":512,"max_output_tokens":512,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.01,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"thenlper/gte-large","prompt_price":0.01,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"intfloat/e5-large-v2","object":"model","created":1626777600,"model_id":"intfloat/e5-large-v2","canonical_slug":"intfloat/e5-large-v2","display_name":"Intfloat: E5 Large V2","description":"The e5-large-v2 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-accuracy semantic embeddings optimized for retrieval, semantic search, reranking, and similarity-scoring tasks.\n\n","model_family":"E5","model_family_id":11,"category_type":"Embeddings","context_length":512,"max_input_tokens":512,"max_output_tokens":512,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.01,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"intfloat/e5-large-v2","prompt_price":0.01,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"intfloat/multilingual-e5-large","object":"model","created":1626777600,"model_id":"intfloat/multilingual-e5-large","canonical_slug":"intfloat/multilingual-e5-large","display_name":"Intfloat: Multilingual E5 Large","description":"The multilingual-e5-large embedding model encodes sentences, paragraphs, and documents across over 90 languages into a 1024-dimensional dense vector space, delivering robust semantic embeddings optimized for multilingual retrieval, cross-language similarity, and large-scale data search.\n\n","model_family":"E5","model_family_id":11,"category_type":"Embeddings","context_length":512,"max_input_tokens":512,"max_output_tokens":512,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.01,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"intfloat/multilingual-e5-large","prompt_price":0.01,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"baai/bge-large-en-v1.5","object":"model","created":1626777600,"model_id":"baai/bge-large-en-v1.5","canonical_slug":"baai/bge-large-en-v1.5","display_name":"BAAI: Bge Large En V1.5","description":"The bge-large-en-v1.5 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-fidelity semantic embeddings optimized for semantic search, document retrieval, and downstream NLP tasks in English.","model_family":"BGE","model_family_id":2,"category_type":"Embeddings","context_length":512,"max_input_tokens":512,"max_output_tokens":512,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.01,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"BAAI/bge-large-en-v1.5","prompt_price":0.01,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"baai/bge-m3","object":"model","created":1626777600,"model_id":"baai/bge-m3","canonical_slug":"baai/bge-m3","display_name":"BAAI: Bge M3","description":"The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.","model_family":"BGE","model_family_id":2,"category_type":"Embeddings","context_length":8192,"max_input_tokens":8192,"max_output_tokens":8192,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.01,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"BAAI/bge-m3","prompt_price":0.01,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-embedding-0.6b","object":"model","created":1626777600,"model_id":"qwen/qwen3-embedding-0.6b","canonical_slug":"qwen/qwen3-embedding-0.6b","display_name":"Qwen: Qwen3 Embeddings 0.6B","description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.","model_family":"Qwen","model_family_id":49,"category_type":"Embeddings","context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.01,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3-Embedding-0.6B","prompt_price":0.01,"completion_price":null,"context_length":32768,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"qwen/qwen3-embedding-0.6b","prompt_price":0.07,"completion_price":null,"context_length":32768,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"nousresearch/hermes-4-14b","object":"model","created":1626777600,"model_id":"nousresearch/hermes-4-14b","canonical_slug":"nousresearch/hermes-4-14b","display_name":"Nous: Hermes 4 14B","description":"Hermes 4 14B is an open-source reasoning model from Nous Research built on Qwen 3 that excels at math, code, logic, and creative tasks","model_family":"Nous","model_family_id":42,"category_type":"LLM","context_length":40960,"max_input_tokens":40960,"max_output_tokens":40960,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.0136,"min_completion_price":0.0543,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"chutes","service_tier":"standard","endpoint_name":"NousResearch/Hermes-4-14B","prompt_price":0.0136,"completion_price":0.0543,"context_length":40960,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"}]},{"id":"qwen/qwen3.7-flash","object":"model","created":1626777600,"model_id":"qwen/qwen3.7-flash","canonical_slug":"qwen/qwen3.7-flash","display_name":"Qwen: Qwen 3.7 Flash","description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world visual perception.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.014,"min_completion_price":0.055,"supported_endpoint_types":["openai"],"provider_count":6,"providers":[{"provider_slug":"alibaba/cn","service_tier":"flex","endpoint_name":"qwen3.7-flash","prompt_price":0.014,"completion_price":0.055,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"qwen3.7-flash","prompt_price":0.014,"completion_price":0.055,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/hk","service_tier":"standard","endpoint_name":"qwen3.7-flash","prompt_price":0.014,"completion_price":0.055,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"qwen3.7-flash","prompt_price":0.014,"completion_price":0.055,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/jp","service_tier":"standard","endpoint_name":"qwen3.7-flash","prompt_price":0.014,"completion_price":0.055,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.7-flash","prompt_price":0.015,"completion_price":0.065,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"voyage/voyage-4-lite","object":"model","created":1626777600,"model_id":"voyage/voyage-4-lite","canonical_slug":"voyage/voyage-4-lite","display_name":"Voyage: voyage 4 lite","description":"Optimized for latency and cost. All embeddings created with the 4 series are compatible with each other","model_family":"Voyage","model_family_id":61,"category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.02,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"voyage","service_tier":"standard","endpoint_name":"voyage-4-lite","prompt_price":0.02,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"voyage/voyage-3.5-lite","object":"model","created":1626777600,"model_id":"voyage/voyage-3.5-lite","canonical_slug":"voyage/voyage-3.5-lite","display_name":"Voyage: voyage 3.5 Lite","description":"Optimized for latency and cost. ","model_family":"Voyage","model_family_id":61,"category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.02,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"voyage","service_tier":"standard","endpoint_name":"voyage-3.5-lite","prompt_price":0.02,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"voyage/voyage-rerank-2.5-lite","object":"model","created":1626777600,"model_id":"voyage/voyage-rerank-2.5-lite","canonical_slug":"voyage/voyage-rerank-2.5-lite","display_name":"Voyage: voyage Rerank 2.5 Lite","description":"Our generalist reranker optimized for both latency and quality with instruction-following and multilingual support. ","model_family":"Voyage","model_family_id":61,"category_type":"Reranker","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.02,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"voyage","service_tier":"standard","endpoint_name":"voyage-rerank-2.5-lite","prompt_price":0.02,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"mistral/mistral-nemo","object":"model","created":1626777600,"model_id":"mistral/mistral-nemo","canonical_slug":"mistral/mistral-nemo","display_name":"Mistral: Mistral Nemo","description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA.\n\nThe model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, and Hindi.\n\nIt supports function calling and is released under the Apache 2.0 license.","model_family":"Mistral","model_family_id":37,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":16400,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.02,"min_completion_price":0.04,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"mistralai/Mistral-Nemo-Instruct-2407","prompt_price":0.02,"completion_price":0.04,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"mistral","service_tier":"standard","endpoint_name":"open-mistral-nemo","prompt_price":0.15,"completion_price":0.15,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/text-embedding-3-small","object":"model","created":1626777600,"model_id":"openai/text-embedding-3-small","canonical_slug":"openai/text-embedding-3-small","display_name":"OpenAI: Text Embedding 3 Small","description":"text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.\n\n","model_family":"OpenAI","model_family_id":43,"category_type":"Embeddings","context_length":8192,"max_input_tokens":8192,"max_output_tokens":8192,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.02,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"text-embedding-3-small","prompt_price":0.02,"completion_price":null,"context_length":8192,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-embedding-4b","object":"model","created":1626777600,"model_id":"qwen/qwen3-embedding-4b","canonical_slug":"qwen/qwen3-embedding-4b","display_name":"Qwen: Qwen3 Embedding 4B","description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.","model_family":"Qwen","model_family_id":49,"category_type":"Embeddings","context_length":32000,"max_input_tokens":32000,"max_output_tokens":32000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.02,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3-Embedding-4B","prompt_price":0.02,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-reranker-4b","object":"model","created":1626777600,"model_id":"qwen/qwen3-reranker-4b","canonical_slug":"qwen/qwen3-reranker-4b","display_name":"Qwen: Qwen3 Reranker 4B","description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B)","model_family":"Qwen","model_family_id":49,"model_version":"3","category_type":"Reranker","context_length":32000,"max_input_tokens":32000,"max_output_tokens":32000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.025,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3-Reranker-4B","prompt_price":0.025,"completion_price":null,"context_length":32000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen-flash","object":"model","created":1626777600,"model_id":"qwen/qwen-flash","canonical_slug":"qwen/qwen-flash","display_name":"Qwen: Qwen Flash","description":"The Qwen3 series Flash models effectively blend thinking and non-thinking modes, allowing switching between modes during dialogue. They exhibit excellent performance on complex reasoning tasks, with significantly improved instruction following and text understanding capabilities. Support for 1MB context lengths is provided, with tiered billing based on context length.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":32000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.025,"min_completion_price":0.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen-flash","prompt_price":0.025,"completion_price":0.2,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-vl-flash","object":"model","created":1626777600,"model_id":"qwen/qwen3-vl-flash","canonical_slug":"qwen/qwen3-vl-flash","display_name":"Qwen: Qwen3-VL-Flash","description":"The Qwen3 series of small-sized visual understanding models effectively integrates thinking and non-thinking modes, outperforming the open-source version Qwen3-VL-30B-A3B with faster response times. It features a comprehensive upgrade in image/video understanding, supporting extended contextual information such as long videos and documents, spatial awareness, and object recognition; it also possesses visual 2D/3D localization capabilities, making it competent for complex real-world tasks.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":32000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.025,"min_completion_price":0.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-vl-flash","prompt_price":0.025,"completion_price":0.2,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"upstage/solar-pro-4","object":"model","created":1626777600,"model_id":"upstage/solar-pro-4","canonical_slug":"upstage/solar-pro-4","display_name":"Upstage: Solar Pro 4","description":"Upstage's flagship text model for agentic, coding, document, and business workflows.","model_family":"Solar","model_family_id":118,"category_type":"LLM","context_length":524288,"max_input_tokens":524288,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.03,"min_completion_price":0.12,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"upstage","service_tier":"standard","endpoint_name":"solar-pro4","prompt_price":0.03,"completion_price":0.12,"context_length":524288,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"inference-net/schematron-v2-turbo","object":"model","created":1626777600,"model_id":"inference-net/schematron-v2-turbo","canonical_slug":"inference-net/schematron-v2-turbo","display_name":"Inference Net: Schematron V2 Turbo","description":"Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather than through system or user prompts.","model_family":"schematron","model_family_id":122,"category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8192,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.03,"min_completion_price":0.15,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"inference.net","service_tier":"standard","endpoint_name":"inference-net/schematron-v2-turbo","prompt_price":0.03,"completion_price":0.15,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"amazon/nova-micro-v1","object":"model","created":1626777600,"model_id":"amazon/nova-micro-v1","canonical_slug":"amazon/nova-micro-v1","display_name":"Amazon: Nova Micro 1.0","description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length of 128K tokens and optimized for speed and cost, Amazon Nova Micro excels at tasks such as text summarization, translation, content classification, interactive chat, and brainstorming. It has  simple mathematical reasoning and coding abilities.","model_family":"Nova","model_family_id":76,"category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":5100,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.035,"min_completion_price":0.14,"supported_endpoint_types":["anthropic","openai"],"provider_count":1,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"us.amazon.nova-micro-v1","prompt_price":0.035,"completion_price":0.14,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen2.5-7b-instruct","object":"model","created":1626777600,"model_id":"qwen/qwen2.5-7b-instruct","canonical_slug":"qwen/qwen2.5-7b-instruct","display_name":"Qwen: Qwen2.5 7B Instruct","description":"Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qwen2.5 brings the following improvements upon Qwen2:\n\nSignificantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized expert models in these domains.\nSignificant improvements in instruction following, generating long texts (over 8K tokens), understanding structured data (e.g, tables), and generating structured outputs especially JSON. More resilient to the diversity of system prompts, enhancing role-play implementation and condition-setting for chatbots.\nLong-context Support up to 128K tokens and can generate up to 8K tokens.\nMultilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.\nThis repo contains the instruction-tuned 7B Qwen2.5 model, which has the following features:\n\nType: Causal Language Models\nTraining Stage: Pretraining \u0026 Post-training\nArchitecture: transformers with RoPE, SwiGLU, RMSNorm, and Attention QKV bias\nNumber of Parameters: 7.61B\nNumber of Paramaters (Non-Embedding): 6.53B\nNumber of Layers: 28\nNumber of Attention Heads (GQA): 28 for Q and 4 for KV\nContext Length: Full 131,072 tokens and generation 8192 tokens\nPlease refer to this section for detailed instructions on how to deploy Qwen2.5 for handling long texts.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":131072,"max_input_tokens":129024,"max_output_tokens":8192,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.04,"min_completion_price":0.1,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"qwen/qwen2.5-7b-instruct","prompt_price":0.04,"completion_price":0.1,"context_length":128000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"z-ai/glm-4.6v-flashx","object":"model","created":1626777600,"model_id":"z-ai/glm-4.6v-flashx","canonical_slug":"z-ai/glm-4.6v-flashx","display_name":"Z.AI: GLM 4.6V FlashX","description":"GLM-4.6 achieves comprehensive enhancements across multiple domains, including real-world coding, long-context processing, reasoning, searching, writing, and agentic applications. Details are as follows:\nLonger context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.\nSuperior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages.\nAdvanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.\nMore capable agents: GLM-4.6 exhibits stronger performance in tool use and search-based agents, and integrates more effectively within agent frameworks.\nRefined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.","model_family":"GLM","model_family_id":17,"model_version":"4.6v","category_type":"LLM","context_length":200000,"max_input_tokens":200000,"max_output_tokens":128000,"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.04,"min_completion_price":0.4,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4.6v-flashx","prompt_price":0.04,"completion_price":0.4,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-ocr","object":"model","created":1626777600,"model_id":"deepseek/deepseek-ocr","canonical_slug":"deepseek/deepseek-ocr","display_name":"DeepSeek: Deepseek OCR","description":"DeepSeek-OCR is a comprehensive Optical Character Recognition (OCR) model that analyzes and understands complex documents. It excels at challenging OCR tasks, including recognizing mathematical formulas and processing text that is curved, rotated, or overlapping.","model_family":"DeepSeek","model_family_id":9,"category_type":"LLM","context_length":8200,"max_input_tokens":8200,"max_output_tokens":8200,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.04,"min_completion_price":0.08,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"deepseek-ai/deepseek-ocr","prompt_price":0.04,"completion_price":0.08,"context_length":8190,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"deepseek-ai/deepseek-ocr-maas","prompt_price":0.3,"completion_price":1.2,"context_length":8200,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"nvidia/nemotron-nano-9b-v2","object":"model","created":1626777600,"model_id":"nvidia/nemotron-nano-9b-v2","canonical_slug":"nvidia/nemotron-nano-9b-v2","display_name":"NVIDIA: Nemotron Nano 9B V2","description":"NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response.\n\nThe model's reasoning capabilities can be controlled via a system prompt. If the user prefers the model to provide its final answer without intermediate reasoning traces, it can be configured to do so.","model_family":"Nemotron","model_family_id":41,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.04,"min_completion_price":0.16,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"nvidia/NVIDIA-Nemotron-Nano-9B-v2","prompt_price":0.04,"completion_price":0.16,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"}]},{"id":"volcengine/doubao-seed-2.0-mini","object":"model","created":1626777600,"model_id":"volcengine/doubao-seed-2.0-mini","canonical_slug":"volcengine/doubao-seed-2.0-mini","display_name":"VolcanoEngine: Doubao-Seed 2.0 Mini","description":"Designed for low-latency, high-concurrency, and cost-sensitive scenarios, it delivers exceptional model inference speed. Model performance is comparable to Doubao-Seed-1.6. It supports 256k context, four levels of think length, and multimodal understanding, making it suitable for lightweight tasks where cost and speed are paramount.","model_family":"Doubao-Seed","model_family_id":66,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.04,"min_completion_price":0.32,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"volcengine","service_tier":"standard","endpoint_name":"ep-20260320164229-cznhl","prompt_price":0.04,"completion_price":0.32,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3.5-4b","object":"model","created":1626777600,"model_id":"qwen/qwen3.5-4b","canonical_slug":"qwen/qwen3.5-4b","display_name":"Qwen3: Qwen3.5-4b","description":"Qwen3.5 4B is a low-cost multimodal reasoning model with 256K context, image and video input, function tools, and structured output.\n\nSupports text, image, and video input, streaming, function tools, structured JSON output, seed control, and thinking mode on by default. Use reasoning_effort or thinking_budget for bounded thinking, or enable_thinking=false for direct answers. Automatic cache reads are billed at the cached-input rate when reported by the model service. Explicit cache controls are not supported.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":32768,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.04,"min_completion_price":0.07,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"empiriolabs","service_tier":"standard","endpoint_name":"qwen3-5-4b","prompt_price":0.04,"completion_price":0.07,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"typesafe/jev-1.13","object":"model","created":1626777600,"model_id":"typesafe/jev-1.13","canonical_slug":"typesafe/jev-1.13","display_name":"TypeSafe: Jev 1.13","description":"System One structured decisions: choice, score and noul. Input $0.042/M tokens; output free.","model_family":"jev","model_family_id":125,"model_version":"1.13.0","category_type":"Decisions","context_length":64000,"max_input_tokens":64000,"input_modalities":["text"],"output_modalities":["decisions"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.042,"min_completion_price":0,"supported_endpoint_types":["decisions"],"provider_count":1,"providers":[{"provider_slug":"typesafe","service_tier":"standard","endpoint_name":"jev-1.13.0","prompt_price":0.042,"completion_price":0,"context_length":64000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-8b","object":"model","created":1626777600,"model_id":"qwen/qwen3-8b","canonical_slug":"qwen/qwen3-8b","display_name":"Qwen: Qwen3 8B","description":"Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between \"thinking\" mode for math, coding, and logical inference, and \"non-thinking\" mode for general conversation. The model is fine-tuned for instruction-following, agent integration, creative writing, and multilingual use across 100+ languages and dialects. It natively supports a 32K token context window and can extend to 131K tokens with YaRN scaling.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8192,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":0.35,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"qwen/qwen3-8b","prompt_price":0.05,"completion_price":0.4,"context_length":32000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-8b","prompt_price":0.09,"completion_price":0.35,"context_length":131100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"}]},{"id":"nvidia/nemotron-3-nano-30b-a3b","object":"model","created":1626777600,"model_id":"nvidia/nemotron-3-nano-30b-a3b","canonical_slug":"nvidia/nemotron-3-nano-30b-a3b","display_name":"NVIDIA: Nemotron 3 Nano 30B A3B","description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.\n\nThe model is fully open with open-weights, datasets and recipes so developers can easily\ncustomize, optimize, and deploy the model on their infrastructure for maximum privacy and\nsecurity.\n\nNote: For the free endpoint, all prompts and output are logged to improve the provider's model and its product and services. Please do not upload any personal, confidential, or otherwise sensitive information. This is a trial use only. Do not use for production or business-critical systems.","model_family":"Nemotron","model_family_id":41,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":0.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"nvidia/Nemotron-3-Nano-30B-A3B","prompt_price":0.05,"completion_price":0.2,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"}]},{"id":"jina/jina-reranker-v3","object":"model","created":1626777600,"model_id":"jina/jina-reranker-v3","canonical_slug":"jina/jina-reranker-v3","display_name":"Jina: Jina Reranker V3","description":"jina-reranker-v3 is a 0.6B parameter multilingual document reranker introducing a novel last but not late interaction architecture. Unlike ColBERT's separate encoding with multi-vector matching, this model performs causal self-attention between query and documents within the same context window, enabling rich cross-document interactions before extracting contextual embeddings from the last token of each document. Built on Qwen3-0.6B with 28 transformer layers and a lightweight MLP projector (1024→512→256), it processes up to 64 documents simultaneously within 131K token context. The model achieves state-of-the-art BEIR performance with 61.94 nDCG-10 while being 10× smaller than generative listwise rerankers.","model_family":"Jina","model_family_id":25,"model_version":"3","category_type":"Reranker","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":0.05,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-reranker-v3","prompt_price":0.05,"completion_price":0.05,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"voyage/voyage-rerank-2.5","object":"model","created":1626777600,"model_id":"voyage/voyage-rerank-2.5","canonical_slug":"voyage/voyage-rerank-2.5","display_name":"Voyage: voyage Rerank 2.5","description":"Our generalist reranker optimized for quality with instruction-following and multilingual support. ","model_family":"Voyage","model_family_id":61,"category_type":"Reranker","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"voyage","service_tier":"standard","endpoint_name":"voyage-rerank-2.5","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"google/gemma-3-4b-it","object":"model","created":1626777600,"model_id":"google/gemma-3-4b-it","canonical_slug":"google/gemma-3-4b-it","display_name":"Google: Gemma 3 4B IT","description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling.","model_family":"Gemma","model_family_id":16,"model_version":"3","category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":0.1,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"google/gemma-3-4b-it","prompt_price":0.05,"completion_price":0.1,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemma-3-12b-it","object":"model","created":1626777600,"model_id":"google/gemma-3-12b-it","canonical_slug":"google/gemma-3-12b-it","display_name":"Google: Gemma 3 12B IT","description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after Gemma 3 27B","model_family":"Gemma","model_family_id":16,"model_version":"3","category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":0.15,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"google/gemma-3-12b-it","prompt_price":0.05,"completion_price":0.15,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"jina/jina-embeddings-v4","object":"model","created":1626777600,"model_id":"jina/jina-embeddings-v4","canonical_slug":"jina/jina-embeddings-v4","display_name":"Jina: Jina Embeddings V4","description":"Jina Embeddings V4 is a 3.8 billion parameter multimodal embedding model that provides unified text and image representation capabilities. Built on the Qwen2.5-VL-3B-Instruct backbone, the model features an architecture that supports both single-vector and multi-vector embeddings in the late interaction style, addressing limitations found in traditional CLIP-style dual-encoder models. The model incorporates three specialized task-specific LoRA adapters (60M parameters each) that optimize performance across different retrieval scenarios including asymmetric query-document retrieval, semantic text similarity, and code search without modifying the frozen backbone weights. The model demonstrates strong performance in processing visually rich content such as tables, charts, diagrams, screenshots, and mixed-media formats through a unified processing pathway that reduces the modality gap present in conventional architectures. Supporting multilingual capabilities, the model can handle input texts up to 32,768 tokens with images resized to 20 megapixels, making it suitable for various document retrieval and cross-modal search applications across different languages and domains.","model_family":"Jina","model_family_id":25,"model_version":"4","category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-embeddings-v4","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-clip-v2","object":"model","created":1626777600,"model_id":"jina/jina-clip-v2","canonical_slug":"jina/jina-clip-v2","display_name":"Jina: Jina Clip V2","description":"Jina CLIP v2 revolutionizes multimodal AI by bridging the gap between visual and textual understanding across 89 languages. This model solves critical challenges in global e-commerce, content management, and cross-cultural communication by enabling accurate image-text matching regardless of language barriers. For businesses expanding internationally or managing multilingual content, it eliminates the need for separate models per language or complex translation pipelines. The model particularly shines in scenarios requiring precise visual search across language boundaries, such as global marketplace product discovery or multilingual digital asset management.","model_family":"Jina","model_family_id":25,"model_version":"4","category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-clip-v2","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-embeddings-v3","object":"model","created":1626777600,"model_id":"jina/jina-embeddings-v3","canonical_slug":"jina/jina-embeddings-v3","display_name":"Jina: Jina Embeddings V3","description":"Jina Embeddings v3 is a groundbreaking multilingual text embedding model that transforms how organizations handle text understanding and retrieval across languages. At its core, it solves the critical challenge of maintaining high performance across multiple languages and tasks while keeping computational requirements manageable. The model particularly shines in production environments where efficiency matters - it achieves state-of-the-art performance with just 570M parameters, making it accessible for teams that can't afford the computational overhead of larger models. Organizations needing to build scalable, multilingual search systems or analyze content across language barriers will find this model especially valuable.","model_family":"Jina","model_family_id":25,"model_version":"4","category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-embeddings-v3","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-colbert-v2","object":"model","created":1626777600,"model_id":"jina/jina-colbert-v2","canonical_slug":"jina/jina-colbert-v2","display_name":"Jina: Jina Colbert V2","description":"Jina-ColBERT-v2 is a groundbreaking multilingual information retrieval model that solves the critical challenge of efficient, high-quality search across multiple languages. As the first multilingual ColBERT-like model to generate compact embeddings, it addresses the growing need for scalable, cost-effective multilingual search solutions in global applications. Organizations dealing with multilingual content, from e-commerce platforms to content management systems, can leverage this model to provide accurate search results across 89 languages while significantly reducing storage and computational costs through its innovative dimension reduction capabilities.","model_family":"Jina","model_family_id":25,"model_version":"4","category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-colbert-v2","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-clip-v1","object":"model","created":1626777600,"model_id":"jina/jina-clip-v1","canonical_slug":"jina/jina-clip-v1","display_name":"Jina: Jina Clip V1","description":"Jina CLIP v1 revolutionizes multimodal AI by being the first model to excel equally in both text-to-text and text-to-image retrieval tasks. Unlike traditional CLIP models that struggle with text-only scenarios, this model achieves state-of-the-art performance across all retrieval combinations while maintaining a remarkably compact 223M parameter size. The model addresses a critical industry challenge by eliminating the need for separate models for text and image processing, reducing system complexity and computational overhead. For teams building search systems, recommendation engines, or content analysis tools, Jina CLIP v1 offers a single, efficient solution that handles both text and visual content with exceptional accuracy.","model_family":"Jina","model_family_id":25,"model_version":"4","category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-clip-v1","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-colbert-v1-en","object":"model","created":1626777600,"model_id":"jina/jina-colbert-v1-en","canonical_slug":"jina/jina-colbert-v1-en","display_name":"Jina: Jina Colbert V1 EN","description":"Jina-ColBERT-v1-en revolutionizes text search by solving a critical challenge in information retrieval: achieving high accuracy without sacrificing computational efficiency. Unlike traditional models that compress entire documents into single vectors, this model maintains precise token-level understanding while requiring only 137M parameters. For teams building search applications, recommendation systems, or content discovery platforms, Jina-ColBERT-v1-en eliminates the traditional trade-off between search quality and system performance. The model particularly shines in scenarios where nuanced text understanding is crucial, such as technical documentation search, academic paper retrieval, or any application where capturing subtle semantic relationships can make the difference between finding the right information and missing critical content.\n","model_family":"Jina","model_family_id":25,"model_version":"4","category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-colbert-v1-en","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-embeddings-v2-base-es","object":"model","created":1626777600,"model_id":"jina/jina-embeddings-v2-base-es","canonical_slug":"jina/jina-embeddings-v2-base-es","display_name":"Jina: Jina Embeddings V2 Base ES","description":"Jina Embeddings v2 Base Spanish is a groundbreaking bilingual text embedding model that addresses the critical challenge of cross-lingual information retrieval and analysis between Spanish and English content. Unlike traditional multilingual models that often show bias towards specific languages, this model delivers truly balanced performance across both Spanish and English, making it indispensable for organizations operating in Spanish-speaking markets or handling bilingual content. The model's most remarkable feature is its ability to generate geometrically aligned embeddings - when texts in Spanish and English express the same meaning, their vector representations naturally cluster together in the embedding space, enabling seamless cross-language search and analysis.","model_family":"Jina","model_family_id":25,"model_version":"4","category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-embeddings-v2-base-es","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-embeddings-v2-base-code","object":"model","created":1626777600,"model_id":"jina/jina-embeddings-v2-base-code","canonical_slug":"jina/jina-embeddings-v2-base-code","display_name":"Jina: Jina Embeddings V2 Base Code","description":"Jina Embeddings v2 Base Code tackles a critical challenge in modern software development: efficiently navigating and understanding large codebases. For development teams struggling with code discovery and documentation, this model transforms how developers interact with code by enabling natural language search across 30 programming languages. Unlike traditional code search tools that rely on exact pattern matching, this model understands the semantic meaning behind code, allowing developers to find relevant code snippets using plain English descriptions. This capability is particularly valuable for teams maintaining large legacy codebases, developers onboarding to new projects, or organizations looking to improve code reuse and documentation practices.","model_family":"Jina","model_family_id":25,"model_version":"4","category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-embeddings-v2-base-code","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-embeddings-v2-base-de","object":"model","created":1626777600,"model_id":"jina/jina-embeddings-v2-base-de","canonical_slug":"jina/jina-embeddings-v2-base-de","display_name":"Jina: Jina Embeddings V2 Base DE","description":"Jina Embeddings v2 Base German addresses a critical challenge in international business: bridging the language gap between German and English markets. For German companies expanding into English-speaking territories, where a third of businesses generate over 20% of their global sales, accurate bilingual understanding is essential. This model transforms how organizations handle cross-language content by enabling seamless text understanding and retrieval in both German and English, making it invaluable for companies implementing international documentation systems, customer support platforms, or content management solutions. Unlike traditional translation-based approaches, this model directly maps equivalent meanings in both languages to the same embedding space, enabling more accurate and efficient bilingual operations.","model_family":"Jina","model_family_id":25,"model_version":"4","category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-embeddings-v2-base-de","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-embeddings-v2-base-zh","object":"model","created":1626777600,"model_id":"jina/jina-embeddings-v2-base-zh","canonical_slug":"jina/jina-embeddings-v2-base-zh","display_name":"Jina: Jina Embeddings V2 Base ZH","description":"Jina Embeddings v2 Base Chinese breaks new ground as the first open-source model to seamlessly handle both Chinese and English text with an unprecedented 8,192 token context length. This bilingual powerhouse addresses a critical challenge in global business: the need for accurate, long-form document processing across Chinese and English content. Unlike traditional models that struggle with cross-lingual understanding or require separate models for each language, this model maps equivalent meanings in both languages to the same embedding space, making it invaluable for organizations expanding globally or managing multilingual content.\n","model_family":"Jina","model_family_id":25,"model_version":"4","category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-embeddings-v2-base-zh","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-embeddings-v2-base-en","object":"model","created":1626777600,"model_id":"jina/jina-embeddings-v2-base-en","canonical_slug":"jina/jina-embeddings-v2-base-en","display_name":"Jina: Jina Embeddings V2 Base EN","description":"Jina Embeddings v2 Base English is a groundbreaking open-source text embedding model that solves the critical challenge of processing long documents while maintaining high accuracy. Organizations struggling with analyzing extensive legal documents, research papers, or financial reports will find this model particularly valuable. It stands out by handling documents up to 8,192 tokens in length—16 times longer than traditional models—while matching the performance of OpenAI's proprietary solutions. With a compact size of 0.27GB and efficient resource usage, it offers an accessible solution for teams seeking to implement advanced document analysis without excessive computational overhead.","model_family":"Jina","model_family_id":25,"model_version":"4","category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-embeddings-v2-base-en","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-reranker-m0","object":"model","created":1626777600,"model_id":"jina/jina-reranker-m0","canonical_slug":"jina/jina-reranker-m0","display_name":"Jina: Jina Reranker m0","description":"jina-reranker-m0 is a groundbreaking multimodal multilingual reranker model designed to rank visual documents across multiple languages. What makes this model exceptional is its ability to process queries alongside visually rich document images—including pages with text, figures, tables, and various layouts—across 29 languages. The model outputs a ranked list of documents ordered by their relevance to the input query. Unlike previous rerankers that struggled with the \"modality gap\" problem (where images clustered near other images while text clustered near text), jina-reranker-m0 unifies textual and visual modalities in a single decoder-only model, creating a seamless multimodal search experience that can rank both images and text documents together effectively.","model_family":"Jina","model_family_id":25,"model_version":"3","category_type":"Reranker","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-reranker-m0","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-reranker-v2-base-multilingual","object":"model","created":1626777600,"model_id":"jina/jina-reranker-v2-base-multilingual","canonical_slug":"jina/jina-reranker-v2-base-multilingual","display_name":"Jina: Jina Reranker V2 Base Multilingual","description":"Jina Reranker v2 Base Multilingual is a cross-encoder model designed to enhance search accuracy across language barriers and data types. This reranker addresses the critical challenge of precise information retrieval in multilingual environments, particularly valuable for global enterprises needing to refine search results across different languages and content types. With support for over 100 languages and unique capabilities in function calling and code search, it serves as a unified solution for teams requiring accurate search refinement across international content, API documentation, and multilingual codebases. The model's compact 278M parameter design makes it particularly appealing for organizations seeking to balance high performance with resource efficiency.","model_family":"Jina","model_family_id":25,"model_version":"2","category_type":"Reranker","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-reranker-v2-base-multilingual","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-reranker-v1-tiny-en","object":"model","created":1626777600,"model_id":"jina/jina-reranker-v1-tiny-en","canonical_slug":"jina/jina-reranker-v1-tiny-en","display_name":"Jina: Jina Reranker V1 Tiny EN","description":"Jina Reranker v1 Tiny English represents a breakthrough in efficient search refinement, designed specifically for organizations requiring high-performance reranking in resource-constrained environments. This model addresses the critical challenge of maintaining search quality while significantly reducing computational overhead and deployment costs. With just 33M parameters - a fraction of typical reranker sizes - it delivers remarkably competitive performance through innovative knowledge distillation techniques. The model's most surprising feature is its ability to process documents nearly five times faster than base models while maintaining over 92% of their accuracy, making enterprise-grade search refinement accessible to applications where computational resources are at a premium.\n","model_family":"Jina","model_family_id":25,"model_version":"1","category_type":"Reranker","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-reranker-v1-tiny-en","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-reranker-v1-turbo-en","object":"model","created":1626777600,"model_id":"jina/jina-reranker-v1-turbo-en","canonical_slug":"jina/jina-reranker-v1-turbo-en","display_name":"Jina: Jina Reranker V1 Turbo EN","description":"Jina Reranker v1 Turbo English addresses a critical challenge in production search systems: the trade-off between result quality and computational efficiency. While traditional rerankers offer improved search accuracy, their computational demands often make them impractical for real-time applications. This model breaks that barrier by delivering 95% of the base model's accuracy while processing documents three times faster and using 75% less memory. For organizations struggling with search latency or computational costs, this model offers a compelling solution that maintains high-quality search refinement while significantly reducing infrastructure requirements and operational costs.","model_family":"Jina","model_family_id":25,"model_version":"1","category_type":"Reranker","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-reranker-v1-turbo-en","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"jina/jina-reranker-v1-base-en","object":"model","created":1626777600,"model_id":"jina/jina-reranker-v1-base-en","canonical_slug":"jina/jina-reranker-v1-base-en","display_name":"Jina: Jina Reranker V1 Base EN","description":"Jina Reranker v1 Base English revolutionizes search result refinement by addressing a critical limitation in traditional vector search systems: the inability to capture nuanced relationships between queries and documents. While vector search with cosine similarity provides fast initial results, it often misses subtle relevance signals that human users intuitively understand. This reranker bridges that gap by performing sophisticated token-level analysis of both queries and documents, delivering a remarkable 20% improvement in search accuracy. For organizations struggling with search precision or implementing RAG systems, this model offers a powerful solution that significantly improves result quality without requiring a complete overhaul of existing search infrastructure.","model_family":"Jina","model_family_id":25,"model_version":"1","category_type":"Reranker","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai","jina-rerank"],"provider_count":1,"providers":[{"provider_slug":"jina","service_tier":"standard","endpoint_name":"jina-reranker-v1-base-en","prompt_price":0.05,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3-embedding-8b","object":"model","created":1626777600,"model_id":"qwen/qwen3-embedding-8b","canonical_slug":"qwen/qwen3-embedding-8b","display_name":"Qwen: Qwen3 Embedding 8B","description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.","model_family":"Qwen","model_family_id":49,"category_type":"Embeddings","context_length":32000,"max_input_tokens":32000,"max_output_tokens":32000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3-Embedding-8B","prompt_price":0.05,"completion_price":null,"context_length":512,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"perplexity/perplexity-search","object":"model","created":1626777600,"model_id":"perplexity/perplexity-search","canonical_slug":"perplexity/perplexity-search","display_name":"Perplexity: Perplexity Search","description":"Get ranked search results from Perplexity’s continuously refreshed index with advanced filtering and customization options.","model_family":"Perplexity","model_family_id":46,"model_version":"1","category_type":"Search","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"min_request_price":0.05,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"perplexity","service_tier":"standard","endpoint_name":"perplexity-search","prompt_price":0.05,"completion_price":null,"request_price":0.05,"context_length":400,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3-reranker-8b","object":"model","created":1626777600,"model_id":"qwen/qwen3-reranker-8b","canonical_slug":"qwen/qwen3-reranker-8b","display_name":"Qwen: Qwen3 Reranker 8B","description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B)","model_family":"Qwen","model_family_id":49,"category_type":"Reranker","context_length":32000,"max_input_tokens":32000,"max_output_tokens":32000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3-Reranker-8B","prompt_price":0.05,"completion_price":null,"context_length":32000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"mistral/mistral-small-24b-instruct-2501","object":"model","created":1626777600,"model_id":"mistral/mistral-small-24b-instruct-2501","canonical_slug":"mistral/mistral-small-24b-instruct-2501","display_name":"Mistral: Mistral Small 3 24B Instruct 2501","description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware.\n\n","model_family":"Mistral","model_family_id":37,"category_type":"LLM","context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.05,"min_completion_price":0.08,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"mistralai/Mistral-Small-24B-Instruct-2501","prompt_price":0.05,"completion_price":0.08,"context_length":32768,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/transcoder/merge-audios","object":"model","created":1626777600,"model_id":"google/transcoder/merge-audios","canonical_slug":"google/transcoder/merge-audios","display_name":"Google Transcoder: Merge Audios","description":"Merge 2–10 ordered audio inputs into one MP3 through the video generations async API.","model_family":"Google","model_family_id":18,"category_type":"Audio to Audio","input_modalities":["audio"],"output_modalities":["audio"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.05,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"google-transcoder","service_tier":"standard","endpoint_name":"google/transcoder/merge-audios","prompt_price":0.05,"completion_price":null,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"inference-net/schematron-v2-small","object":"model","created":1626777600,"model_id":"inference-net/schematron-v2-small","canonical_slug":"inference-net/schematron-v2-small","display_name":"Inference Net: Schematron V2 Small","description":"Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema in response_format rather than through system or user prompts.","model_family":"schematron","model_family_id":122,"category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":4096,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.05,"min_completion_price":0.23,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"inference.net","service_tier":"standard","endpoint_name":"inference-net/schematron-v2-small","prompt_price":0.05,"completion_price":0.23,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"upstage/solar-mini-4","object":"model","created":1626777600,"model_id":"upstage/solar-mini-4","canonical_slug":"upstage/solar-mini-4","display_name":"Upstage: Solar Mini 4","description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response speed and cost matter, with fluent Korean alongside strong English and Japanese, and support for long-context workloads.","model_family":"Solar","model_family_id":118,"category_type":"LLM","context_length":524288,"max_input_tokens":524288,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.05,"min_completion_price":0.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"upstage","service_tier":"standard","endpoint_name":"solar-mini4","prompt_price":0.05,"completion_price":0.2,"context_length":524288,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"nvidia/nemotron-3.5-content-safety","object":"model","created":1626777600,"model_id":"nvidia/nemotron-3.5-content-safety","canonical_slug":"nvidia/nemotron-3.5-content-safety","display_name":"Nvidia: Nemotron 3.5 Content Safety","description":"Nemotron 3.5 Content Safety evaluates the safety of user messages and assistant responses. It produces safety verdicts and can identify violated categories, supporting moderation pipelines, conversation screening and policy evaluation. Custom categories or a custom policy can define the review criteria.\n\n    It accepts text and images and produces text. Reasoning supports working through complex questions and multi-step tasks.","model_family":"Nemotron","model_family_id":41,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.05,"min_completion_price":0.15,"provider_count":1,"providers":[{"provider_slug":"aoru","service_tier":"standard","endpoint_name":"nvidia/nemotron-3.5-content-safety","prompt_price":0.05,"completion_price":0.15,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"qwen/qwen3.8-flash","object":"model","created":1626777600,"model_id":"qwen/qwen3.8-flash","canonical_slug":"qwen/qwen3.8-flash","display_name":"Qwen: Qwen3.8 Flash","description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.0565,"min_completion_price":0.191,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"alibaba/cn","service_tier":"flex","endpoint_name":"qwen3.8-flash","prompt_price":0.0565,"completion_price":0.191,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.8-flash","prompt_price":0.075,"completion_price":0.235,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.8-omni-flash","object":"model","created":1626777600,"model_id":"qwen/qwen3.8-omni-flash","canonical_slug":"qwen/qwen3.8-omni-flash","display_name":"Qwen: Qwen3.8 Omni Flash","description":"Qwen’s next-generation native omni-modal model supports context lengths of up to 1M tokens and natively accepts text, image, audio, and video inputs. Built on the Qwen3.8-Flash-Next architecture, it is designed for agentic capabilities in real-world productivity scenarios. In addition to coding, knowledge work, GUI interaction, and other agentic tasks, it delivers significant performance gains in workflows that require integrated processing of text, images, audio, and video, including video editing, music video creation, film and video production and narration, multimedia summarization, and audio-video dialogue. It supports two-channel and four-channel spatial audio understanding and is compatible with both the DashScope and OpenAI protocols. We recommend installing the companion Qwen-MM-Plugins to help agent frameworks access its native multimodal capabilities.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","audio","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.0565,"min_completion_price":0.191,"supported_endpoint_types":["openai"],"provider_count":5,"providers":[{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"qwen3.8-omni-flash","prompt_price":0.0565,"completion_price":0.191,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/hk","service_tier":"standard","endpoint_name":"qwen3.8-omni-flash","prompt_price":0.0565,"completion_price":0.191,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"qwen3.8-omni-flash","prompt_price":0.0565,"completion_price":0.191,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/jp","service_tier":"standard","endpoint_name":"qwen3.8-omni-flash","prompt_price":0.0565,"completion_price":0.191,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.8-omni-flash","prompt_price":0.075,"completion_price":0.235,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-4.7-flash","object":"model","created":1626777600,"model_id":"z-ai/glm-4.7-flash","canonical_slug":"z-ai/glm-4.7-flash","display_name":"Z.AI: GLM 4.7 Flash","description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.","model_family":"GLM","model_family_id":17,"model_version":"5","category_type":"LLM","context_length":202753,"max_input_tokens":202753,"max_output_tokens":202753,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.06,"min_completion_price":0.4,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"zai-org/GLM-4.7-Flash","prompt_price":0.06,"completion_price":0.4,"context_length":202753,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"gryphe/mythomax-l2-13b","object":"model","created":1626777600,"model_id":"gryphe/mythomax-l2-13b","canonical_slug":"gryphe/mythomax-l2-13b","display_name":"MythoMax L2 13B","description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay.","model_family":"MythoMax","model_family_id":39,"category_type":"LLM","context_length":4096,"max_input_tokens":4096,"max_output_tokens":4096,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.06,"min_completion_price":0.06,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"nextbit","service_tier":"standard","endpoint_name":"mythomax:13b","prompt_price":0.06,"completion_price":0.06,"context_length":4100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int4"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Gryphe/MythoMax-L2-13b","prompt_price":0.4,"completion_price":0.4,"context_length":4096,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"}]},{"id":"voyage/voyage-4","object":"model","created":1626777600,"model_id":"voyage/voyage-4","canonical_slug":"voyage/voyage-4","display_name":"Voyage: voyage 4","description":"Optimized for general-purpose and multilingual retrieval quality. All embeddings created with the 4 series are compatible with each other","model_family":"Voyage","model_family_id":61,"category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.06,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"voyage","service_tier":"standard","endpoint_name":"voyage-4","prompt_price":0.06,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"voyage/voyage-3.5","object":"model","created":1626777600,"model_id":"voyage/voyage-3.5","canonical_slug":"voyage/voyage-3.5","display_name":"Voyage: voyage 3.5","description":"Optimized for general-purpose and multilingual retrieval quality. ","model_family":"Voyage","model_family_id":61,"category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.06,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"voyage","service_tier":"standard","endpoint_name":"voyage-3.5","prompt_price":0.06,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen-mt-lite","object":"model","created":1626777600,"model_id":"qwen/qwen-mt-lite","canonical_slug":"qwen/qwen-mt-lite","display_name":"Qwen: Qwen Mt Lite","description":"Based on the fully upgraded Qwen3 basic text translation model, it supports mutual translation between 32 languages. The model performance and translation effect have been fully upgraded, and it provides more stable terminology customization, format restoration accuracy and domain suggestion capabilities, making the translation more accurate and natural.\n","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":16000,"max_input_tokens":16000,"max_output_tokens":8000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.06,"min_completion_price":0.18,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen-mt-lite","prompt_price":0.06,"completion_price":0.18,"context_length":16000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"amazon/nova-lite-v1","object":"model","created":1626777600,"model_id":"amazon/nova-lite-v1","canonical_slug":"amazon/nova-lite-v1","display_name":"Amazon: Nova Lite 1.0","description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite can handle real-time customer interactions, document analysis, and visual question-answering tasks with high accuracy.\n\nWith an input context of 300K tokens, it can analyze multiple images or up to 30 minutes of video in a single input.","model_family":"Nova","model_family_id":76,"category_type":"LLM","context_length":300000,"max_input_tokens":300000,"max_output_tokens":5100,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.06,"min_completion_price":0.24,"supported_endpoint_types":["anthropic","openai"],"provider_count":1,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"us.amazon.nova-lite-v1","prompt_price":0.06,"completion_price":0.24,"context_length":300000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"inclusionai/ling-3.0-flash","object":"model","created":1626777600,"model_id":"inclusionai/ling-3.0-flash","canonical_slug":"inclusionai/ling-3.0-flash","display_name":"Ling 3.0 Flash","description":"Ling-3.0-flash is a 124B-parameter Mixture-of-Experts (MoE) model, with approximately 5.1B parameters activated per token.\n\nThe model is designed with token efficiency and production-scale agentic inference as key priorities, enabling developers to complete more useful work within constrained token, latency, and serving-cost budgets.","model_family":"Inclusionai","model_family_id":71,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.06,"min_completion_price":0.18,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"novita","service_tier":"standard","endpoint_name":"inclusionai/ling-3.0-flash","prompt_price":0.06,"completion_price":0.18,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"inclusionai/ling-3.0-flash-vl","object":"model","created":1626777600,"model_id":"inclusionai/ling-3.0-flash-vl","canonical_slug":"inclusionai/ling-3.0-flash-vl","display_name":"Inclusionai: Ling 3.0 Flash VL","description":"The multimodal version built on Ling-3.0-flash — 124B total / ~5.5B active per token, with native text, image, and video understanding. It’s mainly designed for multimodal agentic workflows, long-context understanding, and multi-step reasoning.","model_family":"Inclusionai","model_family_id":71,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":32800,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.06,"min_completion_price":0.18,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"inclusionAI/Ling-3.0-flash-VL","prompt_price":0.06,"completion_price":0.18,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"infron-batch/deepseek-v4.1-flash","object":"model","created":1626777600,"model_id":"infron-batch/deepseek-v4.1-flash","canonical_slug":"infron-batch/deepseek-v4.1-flash","display_name":"DeepSeek: Deepseek V4.1 Flash (Batch)","description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the cost-efficient tier of the V4.1 family. DeepSeek reports that it exceeds V4 Pro on performance, speed, and task completion time, so it sits ahead of the previous flagship rather than beneath it.\n\nIt is suited for coding, reasoning, and agentic workflows, and is particularly strong at long-horizon tasks that must run to completion across many steps.","model_family":"DeepSeek","model_family_id":9,"category_type":"Batch","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.06,"min_completion_price":0.24,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"infron/us","service_tier":"standard","endpoint_name":"deepseek-v4.1-flash","prompt_price":0.06,"completion_price":0.24,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"bytedance/seed-1.6-flash","object":"model","created":1626777600,"model_id":"bytedance/seed-1.6-flash","canonical_slug":"bytedance/seed-1.6-flash","display_name":"ByteDance: Seed 1.6 Flash","description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of up to 16k tokens.","model_family":"Seed","model_family_id":51,"model_version":"1.6 flash","category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16400,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.07,"min_completion_price":0.3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"seed-1-6-flash-250715","prompt_price":0.07,"completion_price":0.3,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-coder-30b-a3b-instruct","object":"model","created":1626777600,"model_id":"qwen/qwen3-coder-30b-a3b-instruct","canonical_slug":"qwen/qwen3-coder-30b-a3b-instruct","display_name":"Qwen: Qwen3 Coder 30b A3b Instruct","description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion.\n\nThis model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":160000,"max_input_tokens":160000,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.07,"min_completion_price":0.27,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"novita","service_tier":"standard","endpoint_name":"qwen/qwen3-coder-30b-a3b-instruct","prompt_price":0.07,"completion_price":0.27,"context_length":160000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-4.7-flashx","object":"model","created":1626777600,"model_id":"z-ai/glm-4.7-flashx","canonical_slug":"z-ai/glm-4.7-flashx","display_name":"Z.AI: GLM 4.7 FlashX","description":"Lightweight, high-speed GLM-4.7 variant.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":202752,"max_input_tokens":202752,"max_output_tokens":131100,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.07,"min_completion_price":0.4,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4.7-flashx","prompt_price":0.07,"completion_price":0.4,"context_length":202752,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-next-80b-a3b-instruct","object":"model","created":1626777600,"model_id":"qwen/qwen3-next-80b-a3b-instruct","canonical_slug":"qwen/qwen3-next-80b-a3b-instruct","display_name":"Qwen: Qwen3 Next 80B A3B Instruct","description":"Qwen3-Next-80B-A3B-Instruct is an 80B parameter model with only 3B activated per token that excels at handling ultra-long contexts up to 256K tokens natively while maintaining strong performance across reasoning, coding, and knowledge tasks with exceptional inference efficiency.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262140,"max_input_tokens":262140,"max_output_tokens":32768,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.072,"min_completion_price":0.287,"supported_endpoint_types":["gemini","openai"],"provider_count":7,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"qwen3-next-80b-a3b-instruct","prompt_price":0.072,"completion_price":0.287,"context_length":128000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"qwen3-next-80b-a3b-instruct","prompt_price":0.072,"completion_price":0.287,"context_length":128000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-next-80b-a3b-instruct","prompt_price":0.075,"completion_price":0.6,"context_length":131100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3-Next-80B-A3B-Instruct","prompt_price":0.09,"completion_price":1.1,"context_length":262100,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int16"},{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"qwen/qwen3-next-80b-a3b-instruct-maas","prompt_price":0.15,"completion_price":1.5,"context_length":262100,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int4"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"qwen/qwen3-next-80b-a3b-instruct","prompt_price":0.15,"completion_price":1.5,"context_length":262100,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int4"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"Qwen/Qwen3-Next-80B-A3B-Instruct","prompt_price":0.15,"completion_price":1.5,"context_length":262140,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3-next-80b-a3b-thinking","object":"model","created":1626777600,"model_id":"qwen/qwen3-next-80b-a3b-thinking","canonical_slug":"qwen/qwen3-next-80b-a3b-thinking","display_name":"Qwen: Qwen3 Next 80B A3B Thinking","description":"Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic planning, and reports strong results across knowledge, reasoning, coding, alignment, and multilingual evaluations. Compared with prior Qwen3 variants, it emphasizes stability under long chains of thought and efficient scaling during inference, and it is tuned to follow complex instructions while reducing repetitive or off-task behavior.\n\nThe model is suitable for agent frameworks and tool use (function calling), retrieval-heavy workflows, and standardized benchmarking where step-by-step solutions are required. It supports long, detailed completions and leverages throughput-oriented techniques (e.g., multi-token prediction) for faster generation. Note that it operates in thinking-only mode.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262140,"max_input_tokens":262140,"max_output_tokens":32768,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.075,"min_completion_price":0.6,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-next-80b-a3b-thinking","prompt_price":0.075,"completion_price":0.6,"context_length":131100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"Qwen/Qwen3-Next-80B-A3B-Thinking","prompt_price":0.15,"completion_price":1.5,"context_length":262140,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"google/gemini-2.5-flash-lite","object":"model","created":1626777600,"model_id":"google/gemini-2.5-flash-lite","canonical_slug":"google/gemini-2.5-flash-lite","display_name":"Google: Gemini 2.5 flash lite","description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models.","model_family":"Gemini","model_family_id":15,"model_version":"2.5","category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"input_modalities":["Text","Code","Image","Audio","Video","PDF"],"output_modalities":["Text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.075,"min_completion_price":0.3,"supported_endpoint_types":["gemini","openai"],"provider_count":1,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-2.5-flash-lite","prompt_price":0.075,"completion_price":0.3,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"mistral/mistral-small-24b-instruct-2506","object":"model","created":1626777600,"model_id":"mistral/mistral-small-24b-instruct-2506","canonical_slug":"mistral/mistral-small-24b-instruct-2506","display_name":"Mistral: Mistral Small 3.2 24B Instruct 2506","description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on WildBench and Arena Hard, reduces infinite generations, and delivers gains in tool use and structured output tasks.\n\nIt supports image and text inputs with structured outputs, function/tool calling, and strong performance across coding (HumanEval+, MBPP), STEM (MMLU, MATH, GPQA), and vision benchmarks (ChartQA, DocVQA).","model_family":"Llama","model_family_id":31,"category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.075,"min_completion_price":0.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","prompt_price":0.075,"completion_price":0.2,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"prism-ml/ternary-bonsai-2-27b","object":"model","created":1626777600,"model_id":"prism-ml/ternary-bonsai-2-27b","canonical_slug":"prism-ml/ternary-bonsai-2-27b","display_name":"PrismML Bonsai 2 27B","description":"Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks the language-model weights to roughly 8.5 GB while retaining 98.2% of the base model's average score across PrismML's 14 thinking-mode benchmarks, enabling efficient inference on consumer hardware. The model thinks by default and defaults to xhigh reasoning effort.","model_family":"PrismMl","model_family_id":124,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.075,"min_completion_price":0.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"darkbloom","service_tier":"standard","endpoint_name":"ternary-bonsai-2-27b","prompt_price":0.075,"completion_price":0.5,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-30b-a3b","object":"model","created":1626777600,"model_id":"qwen/qwen3-30b-a3b","canonical_slug":"qwen/qwen3-30b-a3b","display_name":"Qwen: Qwen3 30B A3B","description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance.\n\nSignificantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":40960,"max_input_tokens":40960,"max_output_tokens":32768,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.08,"min_completion_price":0.4,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"qwen/qwen3-30b-a3b","prompt_price":0.08,"completion_price":1.25,"context_length":40960,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-30b-a3b","prompt_price":0.1,"completion_price":0.4,"context_length":131100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"}]},{"id":"qwen/qwen3-32b","object":"model","created":1626777600,"model_id":"qwen/qwen3-32b","canonical_slug":"qwen/qwen3-32b","display_name":"Qwen: Qwen3 32B","description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for tasks like math, coding, and logical inference, and a \"non-thinking\" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":40960,"max_input_tokens":40960,"max_output_tokens":32768,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.08,"min_completion_price":0.24,"supported_endpoint_types":["openai"],"provider_count":3,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-32b","prompt_price":0.08,"completion_price":0.32,"context_length":131100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"},{"provider_slug":"chutes","service_tier":"standard","endpoint_name":"Qwen/Qwen3-32B-TEE","prompt_price":0.08,"completion_price":0.24,"context_length":40960,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"qwen/qwen3-32b","prompt_price":0.1,"completion_price":1.2,"context_length":40960,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3-30b-a3b-thinking-2507","object":"model","created":1626777600,"model_id":"qwen/qwen3-30b-a3b-thinking-2507","canonical_slug":"qwen/qwen3-30b-a3b-thinking-2507","display_name":"Qwen: Qwen3 30B A3B Thinking 2507","description":"Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated from final answers.\n\nCompared to earlier Qwen3-30B releases, this version improves performance across logical reasoning, mathematics, science, coding, and multilingual benchmarks. It also demonstrates stronger instruction following, tool use, and alignment with human preferences. With higher reasoning efficiency and extended output budgets, it is best suited for advanced research, competitive problem solving, and agentic applications requiring structured long-context reasoning.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.08,"min_completion_price":0.4,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"qwen/qwen3-30b-a3b-thinking-2507","prompt_price":0.08,"completion_price":0.4,"context_length":128000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-30b-a3b-thinking-2507","prompt_price":0.1,"completion_price":1.2,"context_length":131100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"}]},{"id":"google/gemma-3-27b-it","object":"model","created":1626777600,"model_id":"google/gemma-3-27b-it","canonical_slug":"google/gemma-3-27b-it","display_name":"Google: Gemma 3 27B IT","description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2","model_family":"Gemma","model_family_id":16,"model_version":"3","category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.08,"min_completion_price":0.16,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"google/gemma-3-27b-it","prompt_price":0.08,"completion_price":0.16,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/embedding-3","object":"model","created":1626777600,"model_id":"z-ai/embedding-3","canonical_slug":"z-ai/embedding-3","display_name":"GLM: Embedding 3","description":"Embedding-3 is the third-generation text embedding model launched by Zhipu AI. Representing a comprehensive upgrade over its predecessors, it offers enhanced semantic understanding capabilities and greater flexibility in selecting vector dimensions. The model supports custom vector dimensions, thereby providing an optimal balance between performance and cost for diverse application scenarios while maintaining high-quality semantic representations.","model_family":"GLM","model_family_id":17,"category_type":"Embeddings","context_length":8000,"max_input_tokens":8000,"max_output_tokens":8000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.08,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"bigmodel","service_tier":"standard","endpoint_name":"embedding-3","prompt_price":0.08,"completion_price":null,"context_length":8000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"nvidia/nvidia-nemotron-3.5-lightning","object":"model","created":1626777600,"model_id":"nvidia/nvidia-nemotron-3.5-lightning","canonical_slug":"nvidia/nvidia-nemotron-3.5-lightning","display_name":"Nvidia: Nvidia Nemotron 3.5 Lightning","description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that benefit from domain-specific customization.","model_family":"Nemotron","model_family_id":41,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":131100,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.08,"min_completion_price":0.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"nvidia/NVIDIA-Nemotron-3.5-Lightning","prompt_price":0.08,"completion_price":0.2,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"apodex/apodex-1.1-mini","object":"model","created":1626777600,"model_id":"apodex/apodex-1.1-mini","canonical_slug":"apodex/apodex-1.1-mini","display_name":"Apodex 1.1 Mini","description":"Apodex's 35B low-latency core model for high-volume tasks.","model_family":"Apodex","model_family_id":119,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.08,"min_completion_price":0.8,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"apodex","service_tier":"standard","endpoint_name":"apodex-1.1-mini","prompt_price":0.08,"completion_price":0.8,"context_length":256000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-4.7-flash-heretic","object":"model","created":1626777600,"model_id":"z-ai/glm-4.7-flash-heretic","canonical_slug":"z-ai/glm-4.7-flash-heretic","display_name":"GLM 4.7 Flash Heretic","description":"Abliterated (Heretic) build of Zhipu GLM 4.7 Flash, fp8: the refusal direction is removed from the weights, reasoning and tool calling are kept. Thinking is on at low effort unless you set reasoning_effort (none/low/medium/high).\n\n    Olafangensan's card identifies this as a modified GLM-4.7-Flash checkpoint built using Heretic 1.1.0. The underlying model is a 30B-total, 3B-active mixture of experts. Its published refusal measurements are checkpoint-author evaluations, not a guarantee for individual requests.\n\n    Unlid declares a 131,072-token context and up to 24,000 output tokens. Input: text; output: text. Tool calling is supported. Reasoning is supported; it can be disabled. Reasoning tokens, when generated, count toward the output budget and are charged as output. Prices are USD per million tokens from the live catalog; missing cache discounts use the normal input price under Unlid billing rules. Limits and capabilities are provider declarations, not results of an inference test.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":24000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.084,"min_completion_price":0.48,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"unlid","service_tier":"standard","endpoint_name":"glm-4.7-flash-heretic","prompt_price":0.084,"completion_price":0.48,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"qwen/qwen3-30b-a3b-instruct-2507","object":"model","created":1626777600,"model_id":"qwen/qwen3-30b-a3b-instruct-2507","canonical_slug":"qwen/qwen3-30b-a3b-instruct-2507","display_name":"Qwen: Qwen3 30B A3B Instruct 2507","description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.3,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-30b-a3b-instruct-2507","prompt_price":0.1,"completion_price":0.4,"context_length":131100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"Qwen/Qwen3-30B-A3B-Instruct-2507","prompt_price":0.1,"completion_price":0.3,"context_length":131070,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"meta-llama/llama-3.1-8b","object":"model","created":1626777600,"model_id":"meta-llama/llama-3.1-8b","canonical_slug":"meta-llama/llama-3.1-8b","display_name":"Meta: Llama 3.1 8B","description":"Meta's Llama 3.1 is a major upgrade, introducing new model sizes. The flagship 405B model rivals top closed-source AI like GPT-4o, while a new, highly efficient 5B model runs on consumer hardware.\n\nKey improvements include a massive 128K context window for all models, enabling analysis of long documents, and significantly enhanced coding capabilities. By keeping the weights open, Llama 3.1 makes state-of-the-art AI more powerful and accessible than ever, from large-scale deployment to personal devices.","model_family":"Llama","model_family_id":31,"category_type":"LLM","context_length":32800,"max_input_tokens":32800,"max_output_tokens":8200,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.1,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"cerebras","service_tier":"standard","endpoint_name":"llama3.1-8b","prompt_price":0.1,"completion_price":0.1,"context_length":32800,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"z-ai/glm-4.6v-flash","object":"model","created":1626777600,"model_id":"z-ai/glm-4.6v-flash","canonical_slug":"z-ai/glm-4.6v-flash","display_name":"Z.AI: GLM 4.6V Flash","description":"GLM-4.6 achieves comprehensive enhancements across multiple domains, including real-world coding, long-context processing, reasoning, searching, writing, and agentic applications. Details are as follows:\nLonger context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.\nSuperior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages.\nAdvanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.\nMore capable agents: GLM-4.6 exhibits stronger performance in tool use and search-based agents, and integrates more effectively within agent frameworks.\nRefined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.","model_family":"GLM","model_family_id":17,"model_version":"4.6v","category_type":"LLM","context_length":200000,"max_input_tokens":200000,"max_output_tokens":128000,"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.1,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4.6v-flash","prompt_price":0.1,"completion_price":0.1,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-4.5-flash","object":"model","created":1626777600,"model_id":"z-ai/glm-4.5-flash","canonical_slug":"z-ai/glm-4.5-flash","display_name":"Z.AI: GLM 4.5 Flash","description":"GLM-4.5 and GLM-4.5-Air are our latest flagship models, purpose-built as foundational models for agent-oriented applications. Both leverage a Mixture-of-Experts (MoE) architecture. GLM-4.5 has a total parameter count of 355B with 32B active parameters per forward pass, while GLM-4.5-Air adopts a more streamlined design with 106B total parameters and 12B active parameters.\nBoth models share a similar training pipeline: an initial pretraining phase on 15 trillion tokens of general-domain data, followed by targeted fine-tuning on datasets covering code, reasoning, and agent-specific tasks. The context length has been extended to 128k tokens, and reinforcement learning was applied to further enhance reasoning, coding, and agent performance.\nGLM-4.5 and GLM-4.5-Air are optimized for tool invocation, web browsing, software engineering, and front-end development. They can be integrated into code-centric agents such as Claude Code and Roo Code, and also support arbitrary agent applications through tool invocation APIs.\nBoth models support hybrid reasoning modes, offering two execution modes: Thinking Mode for complex reasoning and tool usage, and Non-Thinking Mode for instant responses. These modes can be toggled via the thinking.typeparameter (with enabled and disabled settings), and dynamic thinking is enabled by default.","model_family":"GLM","model_family_id":17,"model_version":"4.5 Flash","category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":96000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.1,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4.5-flash","prompt_price":0.1,"completion_price":0.1,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-4-32b-0414-128k","object":"model","created":1626777600,"model_id":"z-ai/glm-4-32b-0414-128k","canonical_slug":"z-ai/glm-4-32b-0414-128k","display_name":"Z.AI: GLM 4 32B 0414 128K","description":"GLM 4 32B is a cost-effective foundation language model.\n\nIt can efficiently perform complex tasks and has significantly enhanced capabilities in tool use, online search, and code-related intelligent tasks.\n\nIt is made by the same lab behind the thudm models.","model_family":"GLM","model_family_id":17,"model_version":"4","category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":96000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.1,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4-32b-0414-128k","prompt_price":0.1,"completion_price":0.1,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/text-embedding-ada-002","object":"model","created":1626777600,"model_id":"openai/text-embedding-ada-002","canonical_slug":"openai/text-embedding-ada-002","display_name":"OpenAI: Text Embedding Ada 002","description":"text-embedding-ada-002 is OpenAI's legacy text embedding model.\n\n","model_family":"OpenAI","model_family_id":43,"category_type":"Embeddings","context_length":8192,"max_input_tokens":8192,"max_output_tokens":8192,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"text-embedding-ada-002","prompt_price":0.1,"completion_price":null,"context_length":8192,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"mistral/mistral-embed-2312","object":"model","created":1626777600,"model_id":"mistral/mistral-embed-2312","canonical_slug":"mistral/mistral-embed-2312","display_name":"Mistral: Mistral Embed 2312","description":"Mistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications. Developed by Mistral AI in late 2023, it produces 1024-dimensional vectors that effectively capture semantic relationships in text.","model_family":"Mistral","model_family_id":37,"category_type":"Embeddings","context_length":8192,"max_input_tokens":8192,"max_output_tokens":8192,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mistral","service_tier":"standard","endpoint_name":"mistral-embed","prompt_price":0.1,"completion_price":null,"context_length":512,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"stepfun/step-3.5-flash","object":"model","created":1626777600,"model_id":"stepfun/step-3.5-flash","canonical_slug":"stepfun/step-3.5-flash","display_name":"StepFun: Step 3.5 Flash","description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. It is a reasoning model that is incredibly speed efficient even at long contexts.","model_family":"Step","model_family_id":81,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"siliconflow","service_tier":"standard","endpoint_name":"stepfun-ai/Step-3.5-Flash","prompt_price":0.1,"completion_price":0.3,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-vl-plus","object":"model","created":1626777600,"model_id":"qwen/qwen3-vl-plus","canonical_slug":"qwen/qwen3-vl-plus","display_name":"Qwen: Qwen3-VL-Plus","description":"The Qwen3 series of visual understanding models effectively integrates thinking and non-thinking modes, achieving world-class performance on public benchmark datasets such as OS World. This version features comprehensive upgrades in visual coding, spatial perception, and multimodal thinking; visual perception and recognition capabilities have been significantly improved, supporting ultra-long video understanding.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":32000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.8,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-vl-plus","prompt_price":0.1,"completion_price":0.8,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"nvidia/nemotron-3-super-120b-a12b","object":"model","created":1626777600,"model_id":"nvidia/nemotron-3-super-120b-a12b","canonical_slug":"nvidia/nemotron-3-super-120b-a12b","display_name":"NVIDIA: Nemotron 3 Super","description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models.\n\nThe model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified.\n\nFully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.","model_family":"Nemotron","model_family_id":41,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","prompt_price":0.1,"completion_price":0.5,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"}]},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","object":"model","created":1626777600,"model_id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","canonical_slug":"nvidia/llama-3.3-nemotron-super-49b-v1.5","display_name":"NVIDIA: Llama 3.3 Nemotron Super 49B V1.5","description":"Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and multi-turn chat, followed by multiple RL stages; Reward-aware Preference Optimization (RPO) for alignment, RL with Verifiable Rewards (RLVR) for step-wise reasoning, and iterative DPO to refine tool-use behavior. A distillation-driven Neural Architecture Search (“Puzzle”) replaces some attention blocks and varies FFN widths to shrink memory footprint and improve throughput, enabling single-GPU (H100/H200) deployment while preserving instruction following and CoT quality.\n\nIn internal evaluations (NeMo-Skills, up to 16 runs, temp = 0.6, top_p = 0.95), the model reports strong reasoning/coding results, e.g., MATH500 pass@1 = 97.4, AIME-2024 = 87.5, AIME-2025 = 82.71, GPQA = 71.97, LiveCodeBench (24.10–25.02) = 73.58, and MMLU-Pro (CoT) = 79.53. The model targets practical inference efficiency (high tokens/s, reduced VRAM) with Transformers/vLLM support and explicit “reasoning on/off” modes (chat-first defaults, greedy recommended when disabled). Suitable for building agents, assistants, and long-context retrieval systems where balanced accuracy-to-cost and reliable tool use matter.","model_family":"Nemotron","model_family_id":41,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.4,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","prompt_price":0.1,"completion_price":0.4,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"z-ai/glm-4-32b","object":"model","created":1626777600,"model_id":"z-ai/glm-4-32b","canonical_slug":"z-ai/glm-4-32b","display_name":"Z.AI: GLM 4 32B","description":"GLM 4 32B is a cost-effective foundation language model.\n\nIt can efficiently perform complex tasks and has significantly enhanced capabilities in tool use, online search, and code-related intelligent tasks.\n\nIt is made by the same lab behind the thudm models.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":32000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.1,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4-32b-0414-128k","prompt_price":0.1,"completion_price":0.1,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"volcengine/doubao-seed-2.0-lite","object":"model","created":1626777600,"model_id":"volcengine/doubao-seed-2.0-lite","canonical_slug":"volcengine/doubao-seed-2.0-lite","display_name":"VolcanoEngine: Doubao-Seed 2.0 Lite","description":"This model offers a balanced approach to performance and cost for high-frequency enterprise scenarios, surpassing the capabilities of its predecessor, Doubao-Seed-1.8. It excels in production-oriented tasks such as unstructured information processing, content creation, search and recommendation, and data analysis, supporting long contexts, multi-source information fusion, multi-step instruction execution, and high-fidelity structured output. It significantly optimizes costs while ensuring stable performance.","model_family":"Doubao-Seed","model_family_id":66,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.57,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"volcengine","service_tier":"standard","endpoint_name":"ep-20260320164147-qk5wd","prompt_price":0.1,"completion_price":0.57,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"mistral/mistral-small-creative","object":"model","created":1626777600,"model_id":"mistral/mistral-small-creative","canonical_slug":"mistral/mistral-small-creative","display_name":"Mistral: Mistral Small Creative","description":"An experimental specialized small model trained on meticulously curated data, designed for creative writing, narrative generation, roleplay and character-driven dialog, general-purpose instruction following and conversational agents.","model_family":"Mistral","model_family_id":37,"category_type":"LLM","context_length":32800,"max_input_tokens":32800,"max_output_tokens":32800,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1,"min_completion_price":0.3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mistral","service_tier":"standard","endpoint_name":"labs-mistral-small-creative","prompt_price":0.1,"completion_price":0.3,"context_length":32800,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.6-luna","object":"model","created":1626777600,"model_id":"openai/gpt-5.6-luna","canonical_slug":"openai/gpt-5.6-luna","display_name":"OpenAI: GPT-5.6 Luna","description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.1,"min_completion_price":0.6,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"openai/flex","service_tier":"flex","endpoint_name":"gpt-5.6-luna","prompt_price":0.1,"completion_price":0.6,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5.6-luna","prompt_price":0.15,"completion_price":0.9,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.6-luna","prompt_price":0.2,"completion_price":1.2,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai/priority","service_tier":"priority","endpoint_name":"gpt-5.6-luna","prompt_price":0.4,"completion_price":2.4,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-haiku-5.5","object":"model","created":1626777600,"model_id":"anthropic/claude-haiku-5.5","canonical_slug":"anthropic/claude-haiku-5.5","display_name":"Claude Haiku 5.5","description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.1,"min_completion_price":0.5,"supported_endpoint_types":["anthropic","openai"],"provider_count":2,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-haiku-5-5","prompt_price":0.1,"completion_price":0.5,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-haiku-5-5","prompt_price":0.1,"completion_price":0.5,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-5.3-flash","object":"model","created":1626777600,"model_id":"z-ai/glm-5.3-flash","canonical_slug":"z-ai/glm-5.3-flash","display_name":"Z.AI: GLM 5.3 Flash","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":131100,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.105,"min_completion_price":0.35,"supported_endpoint_types":["openai"],"provider_count":3,"providers":[{"provider_slug":"tencentcloud","service_tier":"standard","endpoint_name":"glm-5.3-flash","prompt_price":0.105,"completion_price":0.35,"context_length":1024000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-5.3-flash","prompt_price":0.15,"completion_price":0.5,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"zai-org/GLM-5.3-Flash","prompt_price":0.15,"completion_price":0.5,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"}]},{"id":"google/gemini-embedding-001","object":"model","created":1626777600,"model_id":"google/gemini-embedding-001","canonical_slug":"google/gemini-embedding-001","display_name":"Google: Gemini Embedding 001","description":"gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding. This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark (MTEB) Multilingual leaderboard since the experimental launch in March.\n\n","model_family":"Gemini","model_family_id":15,"category_type":"Embeddings","context_length":2048,"max_input_tokens":2048,"max_output_tokens":3072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1125,"min_completion_price":null,"supported_endpoint_types":["gemini","openai"],"provider_count":1,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-embedding-001","prompt_price":0.1125,"completion_price":null,"context_length":2048,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/text-embedding-large-exp-03-07","object":"model","created":1626777600,"model_id":"google/text-embedding-large-exp-03-07","canonical_slug":"google/text-embedding-large-exp-03-07","display_name":"Google: Text Embedding Large Exp 0307","description":"text-embedding-large-exp-03-07","model_family":"Gemini","model_family_id":15,"category_type":"Embeddings","context_length":2048,"max_input_tokens":2048,"max_output_tokens":3072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1125,"min_completion_price":null,"supported_endpoint_types":["gemini","openai"],"provider_count":1,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"text-embedding-large-exp-03-07","prompt_price":0.1125,"completion_price":null,"context_length":2048,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/text-embedding-005","object":"model","created":1626777600,"model_id":"google/text-embedding-005","canonical_slug":"google/text-embedding-005","display_name":"Google: Text Embedding 005","description":"text-embedding-005","model_family":"Gemini","model_family_id":15,"category_type":"Embeddings","context_length":2048,"max_input_tokens":2048,"max_output_tokens":3072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.1125,"min_completion_price":null,"supported_endpoint_types":["gemini","openai"],"provider_count":1,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"text-embedding-005","prompt_price":0.1125,"completion_price":null,"context_length":2048,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-3.5-flash-lite","object":"model","created":1626777600,"model_id":"google/gemini-3.5-flash-lite","canonical_slug":"google/gemini-3.5-flash-lite","display_name":"Google: Gemini 3.5 Flash Lite","description":"Gemini 3.5 Flash Lite is Flash-Lite's first step into the agentic space, prioritizing thinking and tool calling to serve as a quick, efficient, and capable subagent for larger, more complex workflows.\n\nCompared to Gemini 3.1 Flash-Lite, it delivers stronger agentic performance and tool use, more precise and complete document understanding, and improved overall reasoning capabilities, all while retaining Flash-Lite's cost efficiency and high throughput. Customers on Gemini 2.5 Flash can also migrate directly to Gemini 3.5 Flash Lite.","model_family":"Gemini","model_family_id":15,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.1125,"min_completion_price":0.9375,"supported_endpoint_types":["gemini","openai"],"provider_count":3,"providers":[{"provider_slug":"google-vertex/flex","service_tier":"flex","endpoint_name":"gemini-3.5-flash-lite","prompt_price":0.1125,"completion_price":0.9375,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3.5-flash-lite","prompt_price":0.225,"completion_price":1.875,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex/priority","service_tier":"priority","endpoint_name":"gemini-3.5-flash-lite","prompt_price":0.405,"completion_price":3.375,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-v4.1-flash","object":"model","created":1626777600,"model_id":"deepseek/deepseek-v4.1-flash","canonical_slug":"deepseek/deepseek-v4.1-flash","display_name":"DeepSeek: Deepseek V4.1 Flash","description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the cost-efficient tier of the V4.1 family. DeepSeek reports that it exceeds V4 Pro on performance, speed, and task completion time, so it sits ahead of the previous flagship rather than beneath it.\n\nIt is suited for coding, reasoning, and agentic workflows, and is particularly strong at long-horizon tasks that must run to completion across many steps.","model_family":"DeepSeek","model_family_id":9,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.1132,"min_completion_price":0.4524,"supported_endpoint_types":["openai"],"provider_count":11,"providers":[{"provider_slug":"alibaba/cn","service_tier":"flex","endpoint_name":"deepseek-v4.1-flash","prompt_price":0.1132,"completion_price":0.4524,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"deepseek-v4.1-flash","prompt_price":0.1132,"completion_price":0.4524,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/hk","service_tier":"standard","endpoint_name":"deepseek-v4.1-flash","prompt_price":0.1132,"completion_price":0.4524,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"deepseek-v4.1-flash","prompt_price":0.1132,"completion_price":0.4524,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/jp","service_tier":"standard","endpoint_name":"deepseek-v4.1-flash","prompt_price":0.1132,"completion_price":0.4524,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"deepseek-v4.1-flash","prompt_price":0.12,"completion_price":0.48,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"deepseek-v4.1-flash","prompt_price":0.12,"completion_price":0.48,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"volcengine","service_tier":"flex","endpoint_name":"deepseek-v4.1-flash","prompt_price":0.12,"completion_price":0.48,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"tencentcloud","service_tier":"standard","endpoint_name":"deepseek-v4.1-flash","prompt_price":0.12,"completion_price":0.48,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"baidu-cloud","service_tier":"standard","endpoint_name":"deepseek-v4.1-flash","prompt_price":0.12,"completion_price":0.48,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"deepseek","service_tier":"standard","endpoint_name":"deepseek-flash","prompt_price":0.3,"completion_price":1.2,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-235b-a22b-instruct-2507","object":"model","created":1626777600,"model_id":"qwen/qwen3-235b-a22b-instruct-2507","canonical_slug":"qwen/qwen3-235b-a22b-instruct-2507","display_name":"Qwen: Qwen3 235B A22B Instruct 2507","description":"Qwen3-235B-A22B-Instruct-2507 has the following features:\n\nType: Causal Language Models\nTraining Stage: Pretraining \u0026 Post-training\nNumber of Parameters: 235B in total and 22B activated\nNumber of Paramaters (Non-Embedding): 234B\nNumber of Layers: 94\nNumber of Attention Heads (GQA): 64 for Q and 4 for KV\nNumber of Experts: 128\nNumber of Activated Experts: 8\nContext Length: 262,144 natively and extendable up to 1,010,000 tokens\nNOTE: This model supports only non-thinking mode and does not generate \u003cthink\u003e\u003c/think\u003e blocks in its output. Meanwhile, specifying enable_thinking=False is no longer required.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":131072,"max_input_tokens":129024,"max_output_tokens":8192,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.115,"min_completion_price":0.46,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-235b-a22b-instruct-2507","prompt_price":0.115,"completion_price":0.46,"context_length":131100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"Qwen/Qwen3-235B-A22B-Instruct-2507","prompt_price":0.2,"completion_price":0.88,"context_length":131070,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3-235b-a22b-thinking-2507","object":"model","created":1626777600,"model_id":"qwen/qwen3-235b-a22b-thinking-2507","canonical_slug":"qwen/qwen3-235b-a22b-thinking-2507","display_name":"Qwen: Qwen3 235B A22B Thinking 2507","description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This \"thinking-only\" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode (\u003c/think\u003e) and is designed for high-token outputs (up to 81,920 tokens) in challenging domains.\n\nThe model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.115,"min_completion_price":1.15,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-235b-a22b-thinking-2507","prompt_price":0.115,"completion_price":1.15,"context_length":131100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"qwen/qwen3-235b-a22b-thinking-2507","prompt_price":0.28,"completion_price":2.3,"context_length":128000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"voyage/voyage-4-large","object":"model","created":1626777600,"model_id":"voyage/voyage-4-large","canonical_slug":"voyage/voyage-4-large","display_name":"Voyage: voyage 4 Large","description":"The best general-purpose and multilingual retrieval quality. All embeddings created with the 4 series are compatible with each other","model_family":"Voyage","model_family_id":61,"category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.12,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"voyage","service_tier":"standard","endpoint_name":"voyage-4-large","prompt_price":0.12,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"voyage/voyage-finance-2","object":"model","created":1626777600,"model_id":"voyage/voyage-finance-2","canonical_slug":"voyage/voyage-finance-2","display_name":"Voyage: voyage Finance 2","description":"Optimized for finance retrieval and RAG.","model_family":"Voyage","model_family_id":61,"category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.12,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"voyage","service_tier":"standard","endpoint_name":"voyage-finance-2","prompt_price":0.12,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"voyage/voyage-law-2","object":"model","created":1626777600,"model_id":"voyage/voyage-law-2","canonical_slug":"voyage/voyage-law-2","display_name":"Voyage: voyage Law 2","description":"Optimized for legal retrieval and RAG. Also improved performance across all domains. ","model_family":"Voyage","model_family_id":61,"category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.12,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"voyage","service_tier":"standard","endpoint_name":"voyage-law-2","prompt_price":0.12,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"voyage/voyage-code-2","object":"model","created":1626777600,"model_id":"voyage/voyage-code-2","canonical_slug":"voyage/voyage-code-2","display_name":"Voyage: voyage Code 2","description":"Optimized for code retrieval (17% better than alternatives) / Previous generation of code embeddings.","model_family":"Voyage","model_family_id":61,"category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.12,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"voyage","service_tier":"standard","endpoint_name":"voyage-code-2","prompt_price":0.12,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"openai/text-embedding-3-large","object":"model","created":1626777600,"model_id":"openai/text-embedding-3-large","canonical_slug":"openai/text-embedding-3-large","display_name":"OpenAI: Text Embedding 3 Large","description":"text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.\n\n","model_family":"OpenAI","model_family_id":43,"category_type":"Embeddings","context_length":8192,"max_input_tokens":8192,"max_output_tokens":8192,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.13,"min_completion_price":0.13,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"text-embedding-3-large","prompt_price":0.13,"completion_price":0.13,"context_length":8192,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"volcengine/doubao-seed-1.8","object":"model","created":1626777600,"model_id":"volcengine/doubao-seed-1.8","canonical_slug":"volcengine/doubao-seed-1.8","display_name":"VolcanoEngine: Doubao-Seed 1.8","description":"Doubao-Seed-1.8 is optimized for multimodal agent scenarios. In terms of agent capabilities, tool use and complex command compliance have been significantly enhanced. Regarding multimodal understanding, basic visual capabilities have been significantly improved, enabling low-frame-rate understanding of extremely long videos. Video motion understanding, complex spatial understanding, and document structure parsing capabilities have also been optimized, and intelligent context management is now supported, allowing users to configure context strategies.","model_family":"Doubao-Seed","model_family_id":66,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":32000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.13,"min_completion_price":1.25,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"volcengine","service_tier":"standard","endpoint_name":"ep-20260320164349-jtxwt","prompt_price":0.13,"completion_price":1.25,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"tencent/hy3","object":"model","created":1626777600,"model_id":"tencent/hy3","canonical_slug":"tencent/hy3","display_name":"Tencent: HY3","description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort: a direct no-think mode by default, plus low and high chain-of-thought modes for complex math, coding, and multi-step problems. With a 256K context window, Hy3 targets long-horizon tasks, including improved coreference resolution, multi-turn constraint tracking, and stable tool-calling that generalizes across agent scaffoldings.\n\nTencent positions it as a reliable, cost-effective option across coding, document processing, financial analysis, game development, and frontend design, with a strong emphasis on grounded, anti-hallucination behavior that answers when grounded and flags when evidence is missing rather than fabricating.","model_family":"Hunyuan","model_family_id":24,"category_type":"LLM","context_length":202752,"max_input_tokens":202752,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.132,"min_completion_price":0.528,"supported_endpoint_types":["openai"],"provider_count":5,"providers":[{"provider_slug":"tencentcloud","service_tier":"standard","endpoint_name":"hy3","prompt_price":0.132,"completion_price":0.528,"context_length":256000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"tencent/Hy3","prompt_price":0.14,"completion_price":0.58,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"tencent/hy3","prompt_price":0.14,"completion_price":0.58,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"gmicloud","service_tier":"standard","endpoint_name":"tencent/Hy3","prompt_price":0.14,"completion_price":0.58,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"tencent/hy3","prompt_price":0.2,"completion_price":0.8,"context_length":202752,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"meta-llama/llama-3.3-70b-instruct","object":"model","created":1626777600,"model_id":"meta-llama/llama-3.3-70b-instruct","canonical_slug":"meta-llama/llama-3.3-70b-instruct","display_name":"Meta: Llama 3.3 70B Instruct","description":"This model delivers enhanced performance for chat, coding, instruction following, mathematics, and reasoning use cases.","model_family":"Llama","model_family_id":31,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":120000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.135,"min_completion_price":0.4,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"novita","service_tier":"standard","endpoint_name":"meta-llama/llama-3.3-70b-instruct","prompt_price":0.135,"completion_price":0.4,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.7-plus","object":"model","created":1626777600,"model_id":"qwen/qwen3.7-plus","canonical_slug":"qwen/qwen3.7-plus","display_name":"Qwen: Qwen3.7 Plus","description":"Among the Qwen3.7 series, the cost-effective Plus model builds on its robust text capabilities while delivering a comprehensive upgrade to its vision‑language abilities, all while preserving its full‑stack agent‑level intelligence for coding, tool use, and productivity workflows. Its key distinguishing feature is multi‑modal interactive hybrid agent capabilities, enabling it to perceive real‑world scenes, read screens and interact with GUIs, generate code based on visual references, and perform end‑to‑end navigation within mobile apps.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.138,"min_completion_price":0.5505,"supported_endpoint_types":["openai"],"provider_count":6,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"qwen3.7-plus","prompt_price":0.138,"completion_price":0.5505,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"qwen3.7-plus","prompt_price":0.138,"completion_price":0.5505,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/hk","service_tier":"standard","endpoint_name":"qwen3.7-plus","prompt_price":0.138,"completion_price":0.5505,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"qwen3.7-plus","prompt_price":0.138,"completion_price":0.5505,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/jp","service_tier":"standard","endpoint_name":"qwen3.7-plus","prompt_price":0.138,"completion_price":0.5505,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.7-plus","prompt_price":0.2,"completion_price":0.8,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"xiaomi/mimo-v2.6-flash","object":"model","created":1626777600,"model_id":"xiaomi/mimo-v2.6-flash","canonical_slug":"xiaomi/mimo-v2.6-flash","display_name":"Xiaomi: Mimo V2.6 Flash","description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for greater computational efficiency. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers strong performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.","model_family":"MiMo","model_family_id":35,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.14,"min_completion_price":0.28,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xiaomi","service_tier":"standard","endpoint_name":"mimo-v2.6-flash","prompt_price":0.14,"completion_price":0.28,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemma-4-31b-it-abliterated-v2","object":"model","created":1626777600,"model_id":"google/gemma-4-31b-it-abliterated-v2","canonical_slug":"google/gemma-4-31b-it-abliterated-v2","display_name":"Gemma 4 31B Abliterated","description":"huihui-ai's second abliteration of Google Gemma 4 31B instruct: refusals removed from the weights, vision and tool calling kept. Answers directly, without a thinking phase.\n\n    Huihui-ai's v2 checkpoint is a separate modification of Google's Gemma 4 31B instruction model. Its card states that the first five layers are retained without abliteration. Unlid currently disables the thinking phase on this endpoint because its upstream does not separate reasoning reliably from answer text; do not infer active reasoning support from the base model.\n\n    Unlid declares a 32,768-token context and up to 32,768 output tokens. Input: text, image; output: text. Tool calling is supported. No reasoning mode is declared in the structured catalog. Reasoning tokens, when generated, count toward the output budget and are charged as output. Prices are USD per million tokens from the live catalog; missing cache discounts use the normal input price under Unlid billing rules. Limits and capabilities are provider declarations, not results of an inference test.","model_family":"Gemma","model_family_id":16,"category_type":"LLM","context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.144,"min_completion_price":0.432,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"unlid","service_tier":"standard","endpoint_name":"gemma-4-31b-abliterated","prompt_price":0.144,"completion_price":0.432,"context_length":32768,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-coder-flash","object":"model","created":1626777600,"model_id":"qwen/qwen3-coder-flash","canonical_slug":"qwen/qwen3-coder-flash","display_name":"Qwen: Qwen3 Coder Flash","description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling and environment interaction, combining coding proficiency with versatile general-purpose abilities.\n\n","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.15,"min_completion_price":0.75,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-coder-flash","prompt_price":0.15,"completion_price":0.75,"context_length":131100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"}]},{"id":"minimax/minimax-m2.5","object":"model","created":1626777600,"model_id":"minimax/minimax-m2.5","canonical_slug":"minimax/minimax-m2.5","display_name":"MiniMax: MiniMax M2.5","description":"MiniMax M2.5 is SOTA in coding, agentic tool use and search, office work, and a range of other economically valuable tasks, boasting scores of 80.2% in SWE-Bench Verified, 51.3% in Multi-SWE-Bench, and 76.3% in BrowseComp (with context management).","model_family":"MiniMax","model_family_id":36,"model_version":"2.5","category_type":"LLM","context_length":204800,"max_input_tokens":204800,"max_output_tokens":131000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.15,"min_completion_price":0.6065,"supported_endpoint_types":["openai"],"provider_count":8,"providers":[{"provider_slug":"chutes","service_tier":"standard","endpoint_name":"MiniMaxAI/MiniMax-M2.5-TEE","prompt_price":0.15,"completion_price":1.2,"context_length":196610,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"alibaba/cn/flex","service_tier":"flex","endpoint_name":"MiniMax-M2.5","prompt_price":0.152,"completion_price":0.6065,"context_length":200000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"canopywave","service_tier":"standard","endpoint_name":"minimax/minimax-m2.5","prompt_price":0.27,"completion_price":1.08,"context_length":205000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"minimaxai/minimax-m2.5","prompt_price":0.295,"completion_price":1.2,"context_length":196610,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"minimax","service_tier":"standard","endpoint_name":"MiniMax-M2.5","prompt_price":0.3,"completion_price":1.2,"context_length":204800,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"minimax/minimax-m2.5","prompt_price":0.3,"completion_price":1.2,"context_length":204800,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"sophgo","service_tier":"standard","endpoint_name":"MiniMax-M2.5","prompt_price":0.33,"completion_price":1.32,"context_length":204800,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"minimax/highspeed","service_tier":"priority","endpoint_name":"MiniMax-M2.5-highspeed","prompt_price":0.6,"completion_price":2.4,"context_length":204800,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"mistral/codestral-embed-2505","object":"model","created":1626777600,"model_id":"mistral/codestral-embed-2505","canonical_slug":"mistral/codestral-embed-2505","display_name":"Mistral: Codestral Embed 2505","description":"Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.","model_family":"Mistral","model_family_id":37,"category_type":"Embeddings","context_length":8192,"max_input_tokens":8192,"max_output_tokens":8192,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.15,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mistral","service_tier":"standard","endpoint_name":"codestral-embed","prompt_price":0.15,"completion_price":null,"context_length":512,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"meta-llama/llama-4-maverick","object":"model","created":1626777600,"model_id":"meta-llama/llama-4-maverick","canonical_slug":"meta-llama/llama-4-maverick","display_name":"Meta: Llama 4 Maverick","description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). It supports multilingual text and image input, and produces multilingual text and code output across 12 supported languages. Optimized for vision-language tasks, Maverick is instruction-tuned for assistant-like behavior, image reasoning, and general-purpose multimodal interaction.\n\nMaverick features early fusion for native multimodality and a 1 million token context window. It was trained on a curated mixture of public, licensed, and Meta-platform data, covering ~22 trillion tokens, with a knowledge cutoff in August 2024. Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput.","model_family":"Llama","model_family_id":31,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":16400,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.15,"min_completion_price":0.6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","prompt_price":0.15,"completion_price":0.6,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"}]},{"id":"perceptron/perceptron-mk1","object":"model","created":1626777600,"model_id":"perceptron/perceptron-mk1","canonical_slug":"perceptron/perceptron-mk1","display_name":"Perceptron: Perceptron Mk1","description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding responses, either structured or natural language. It excels at video understanding tasks like video QA, summarization, and event detection. On image inputs, it advances point-by-example grounding from multimodal prompts, OCR and document parsing on messy real-world inputs, open vocabulary object detection and counting, and hand pose estimation.\n\nReasoning can be enabled per request to trade latency for deeper analysis on harder tasks.","model_family":"perceptron","model_family_id":85,"category_type":"LLM","context_length":32000,"max_input_tokens":32000,"max_output_tokens":32000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.15,"min_completion_price":1.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"perceptron","service_tier":"standard","endpoint_name":"perceptron-mk1","prompt_price":0.15,"completion_price":1.5,"context_length":32000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"kwaipilot/kat-coder-air-v2.5","object":"model","created":1626777600,"model_id":"kwaipilot/kat-coder-air-v2.5","canonical_slug":"kwaipilot/kat-coder-air-v2.5","display_name":"Kwaipilot: Kat Coder Air V2.5","description":"Fast, lightweight coding model designed for interactive development, rapid code iteration, and efficient coding agents.","model_family":"Kwaipilot","model_family_id":73,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.15,"min_completion_price":0.6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"kwaipilot/kat-coder-air-v2.5","prompt_price":0.15,"completion_price":0.6,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"upstage/solar-pro-3","object":"model","created":1626777600,"model_id":"upstage/solar-pro-3","canonical_slug":"upstage/solar-pro-3","display_name":"Upstage: Solar Pro 3","description":"Upstage's Mixture-of-Experts text model for reasoning and instruction following.","model_family":"Solar","model_family_id":118,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.15,"min_completion_price":0.6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"upstage","service_tier":"standard","endpoint_name":"solar-pro3","prompt_price":0.15,"completion_price":0.6,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"perceptron/perceptron-mk1.5","object":"model","created":1626777600,"model_id":"perceptron/perceptron-mk1.5","canonical_slug":"perceptron/perceptron-mk1.5","display_name":"Perceptron Mk1.5","description":"Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks, and clips.","model_family":"perceptron","model_family_id":85,"category_type":"LLM","context_length":36864,"max_input_tokens":36864,"max_output_tokens":8192,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.15,"min_completion_price":1.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"perceptron","service_tier":"standard","endpoint_name":"perceptron-mk1.5","prompt_price":0.15,"completion_price":1.5,"context_length":36864,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-v4-flash-0731","object":"model","created":1626777600,"model_id":"deepseek/deepseek-v4-flash-0731","canonical_slug":"deepseek/deepseek-v4-flash-0731","display_name":"DeepSeek: Deepseek V4 Flash 0731","description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.","model_family":"DeepSeek","model_family_id":9,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.1696,"min_completion_price":0.5088,"supported_endpoint_types":["openai"],"provider_count":9,"providers":[{"provider_slug":"alibaba/cn/flex","service_tier":"flex","endpoint_name":"deepseek-v4-flash-0731","prompt_price":0.1696,"completion_price":0.5088,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"deepseek-v4-flash-0731","prompt_price":0.1696,"completion_price":0.5088,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/hk","service_tier":"standard","endpoint_name":"deepseek-v4-flash-0731","prompt_price":0.1696,"completion_price":0.5088,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"deepseek-v4-flash-0731","prompt_price":0.1696,"completion_price":0.5088,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/jp","service_tier":"standard","endpoint_name":"deepseek-v4-flash-0731","prompt_price":0.1696,"completion_price":0.5088,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"deepseek-v4-flash-0731","prompt_price":0.176,"completion_price":0.528,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"tencentcloud","service_tier":"standard","endpoint_name":"deepseek-v4-flash-0731","prompt_price":0.352,"completion_price":1.056,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"deepseek","service_tier":"standard","endpoint_name":"deepseek-v4-flash","prompt_price":0.44,"completion_price":1.32,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"baidu-cloud","service_tier":"flex","endpoint_name":"deepseek-v4-flash-0731","prompt_price":0.44,"completion_price":1.32,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"qwen/qwen3-14b","object":"model","created":1626777600,"model_id":"qwen/qwen3-14b","canonical_slug":"qwen/qwen3-14b","display_name":"Qwen: Qwen3 14B","description":"Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.\n\n","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":40960,"max_input_tokens":40960,"max_output_tokens":8192,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.175,"min_completion_price":0.7,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-14b","prompt_price":0.175,"completion_price":0.7,"context_length":131100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"}]},{"id":"voyage/voyage-3-large","object":"model","created":1626777600,"model_id":"voyage/voyage-3-large","canonical_slug":"voyage/voyage-3-large","display_name":"Voyage: voyage 3 Large","description":"The best general-purpose and multilingual retrieval quality. ","model_family":"Voyage","model_family_id":61,"category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.18,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"voyage","service_tier":"standard","endpoint_name":"voyage-3-large","prompt_price":0.18,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"voyage/voyage-code-3","object":"model","created":1626777600,"model_id":"voyage/voyage-code-3","canonical_slug":"voyage/voyage-code-3","display_name":"Voyage: voyage code 3","description":"Optimized for code retrieval. ","model_family":"Voyage","model_family_id":61,"category_type":"Embeddings","context_length":400,"max_input_tokens":400,"max_output_tokens":10000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.18,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"voyage","service_tier":"standard","endpoint_name":"voyage-code-3","prompt_price":0.18,"completion_price":null,"context_length":400,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3-coder-next","object":"model","created":1626777600,"model_id":"qwen/qwen3-coder-next","canonical_slug":"qwen/qwen3-coder-next","display_name":"Qwen: Qwen3 Coder Next","description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment.\n\nThe model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit \u003cthink\u003e blocks, simplifying integration for production coding agents.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.18,"min_completion_price":1.35,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"qwen/qwen3-coder-next","prompt_price":0.18,"completion_price":1.35,"context_length":262140,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"google/supergemma4-26b-uncensored","object":"model","created":1626777600,"model_id":"google/supergemma4-26b-uncensored","canonical_slug":"google/supergemma4-26b-uncensored","display_name":"SuperGemma 4 26B Uncensored","description":"Community uncensored fine-tune of Google Gemma 4 26B A4B (26B total, 4B active), served as an int4 GGUF. Vision, tool calling, logprobs.\n\n    Jiunsong's supergemma4-26b-uncensored-gguf-v2 repository provides the v2 GGUF Q4_K_M release derived from the SuperGemma Fast line, based on Gemma 4 26B A4B. It emphasizes conversational and coding workloads and a neutral chat template. The card positions this as a text-focused release, whereas Unlid advertises vision; that hosting claim requires an image-input test before relying on it.\n\n    Unlid declares a 256,000-token context and up to 8,192 output tokens. Input: text, image; output: text. Tool calling is supported. No reasoning mode is declared in the structured catalog. Reasoning tokens, when generated, count toward the output budget and are charged as output. Prices are USD per million tokens from the live catalog; missing cache discounts use the normal input price under Unlid billing rules. Limits and capabilities are provider declarations, not results of an inference test.","model_family":"Gemma","model_family_id":16,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8192,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.195,"min_completion_price":0.6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"unlid","service_tier":"standard","endpoint_name":"supergemma4-26b-uncensored","prompt_price":0.195,"completion_price":0.6,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int4"}]},{"id":"z-ai/glm-4.5-air","object":"model","created":1626777600,"model_id":"z-ai/glm-4.5-air","canonical_slug":"z-ai/glm-4.5-air","display_name":"Z.AI: GLM 4.5 Air","description":"GLM-4.5 and GLM-4.5-Air are our latest flagship models, purpose-built as foundational models for agent-oriented applications. Both leverage a Mixture-of-Experts (MoE) architecture. GLM-4.5 has a total parameter count of 355B with 32B active parameters per forward pass, while GLM-4.5-Air adopts a more streamlined design with 106B total parameters and 12B active parameters.\nBoth models share a similar training pipeline: an initial pretraining phase on 15 trillion tokens of general-domain data, followed by targeted fine-tuning on datasets covering code, reasoning, and agent-specific tasks. The context length has been extended to 128k tokens, and reinforcement learning was applied to further enhance reasoning, coding, and agent performance.\nGLM-4.5 and GLM-4.5-Air are optimized for tool invocation, web browsing, software engineering, and front-end development. They can be integrated into code-centric agents such as Claude Code and Roo Code, and also support arbitrary agent applications through tool invocation APIs.\nBoth models support hybrid reasoning modes, offering two execution modes: Thinking Mode for complex reasoning and tool usage, and Non-Thinking Mode for instant responses. These modes can be toggled via the thinking.typeparameter (with enabled and disabled settings), and dynamic thinking is enabled by default.","model_family":"GLM","model_family_id":17,"model_version":"4.5air","category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":96000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.2,"min_completion_price":1.1,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4.5-air","prompt_price":0.2,"completion_price":1.1,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-chat-v3-0324","object":"model","created":1626777600,"model_id":"deepseek/deepseek-chat-v3-0324","canonical_slug":"deepseek/deepseek-chat-v3-0324","display_name":"Deepseek: Deepseek Chat V3 0324","description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.\n\nIt succeeds the DeepSeek V3 model and performs really well on a variety of tasks.","model_family":"DeepSeek","model_family_id":9,"model_version":"v3","category_type":"LLM","context_length":163840,"max_input_tokens":163840,"max_output_tokens":163840,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.2,"min_completion_price":0.77,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"deepseek-ai/DeepSeek-V3-0324","prompt_price":0.2,"completion_price":0.77,"context_length":163840,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"deepseek-ai/DeepSeek-V3-0324","prompt_price":0.216,"completion_price":0.88,"context_length":131070,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen-plus","object":"model","created":1626777600,"model_id":"qwen/qwen-plus","canonical_slug":"qwen/qwen-plus","display_name":"Qwen: Qwen Plus","description":"The enhanced version of the Qianwen ultra-large-scale language model supports input in different languages, including Chinese and English. Compared to previous versions, its Chinese and English coding capabilities, logical reasoning capabilities, and multilingual capabilities have been significantly improved. The response style has been greatly adjusted to cater to human preferences, and the level of detail and clarity of the model's responses has been significantly enhanced. Targeted improvements have been made to its capabilities in creative writing, JSON format compliance, and role-playing.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":32800,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.2,"min_completion_price":0.6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen-plus","prompt_price":0.2,"completion_price":0.6,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"meituan/longcat-flash-chat","object":"model","created":1626777600,"model_id":"meituan/longcat-flash-chat","canonical_slug":"meituan/longcat-flash-chat","display_name":"Meituan: LongCat Flash Chat","description":"LongCat-Flash-Chat is a large-scale Mixture-of-Experts (MoE) model with 560B total parameters, of which 18.6B–31.3B (≈27B on average) are dynamically activated per input. It introduces a shortcut-connected MoE design to reduce communication overhead and achieve high throughput while maintaining training stability through advanced scaling strategies such as hyperparameter transfer, deterministic computation, and multi-stage optimization.\n\nThis release, LongCat-Flash-Chat, is a non-thinking foundation model optimized for conversational and agentic tasks. It supports long context windows up to 128K tokens and shows competitive performance across reasoning, coding, instruction following, and domain benchmarks, with particular strengths in tool use and complex multi-step interactions.","model_family":"LongCat","model_family_id":32,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":32800,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.2,"min_completion_price":0.8,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"meituan-longcat/LongCat-Flash-Chat","prompt_price":0.2,"completion_price":0.8,"context_length":131070,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"mistral/ministral-14b-2512","object":"model","created":1626777600,"model_id":"mistral/ministral-14b-2512","canonical_slug":"mistral/ministral-14b-2512","display_name":"Mistral: Ministral 3 14B 2512","description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language model with vision capabilities.","model_family":"Mistral","model_family_id":37,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.2,"min_completion_price":0.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mistral","service_tier":"standard","endpoint_name":"ministral-14b-2512","prompt_price":0.2,"completion_price":0.2,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"nvidia/nemotron-nano-12b-v2-vl","object":"model","created":1626777600,"model_id":"nvidia/nemotron-nano-12b-v2-vl","canonical_slug":"nvidia/nemotron-nano-12b-v2-vl","display_name":"NVIDIA: Nemotron Nano 12B 2 VL","description":"NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s memory-efficient sequence modeling for significantly higher throughput and lower latency.\n\nThe model supports inputs of text and multi-image documents, producing natural-language outputs. It is trained on high-quality NVIDIA-curated synthetic datasets optimized for optical-character recognition, chart reasoning, and multimodal comprehension.\n\nNemotron Nano 2 VL achieves leading results on OCRBench v2 and scores ≈ 74 average across MMMU, MathVista, AI2D, OCRBench, OCR-Reasoning, ChartQA, DocVQA, and Video-MME—surpassing prior open VL baselines. With Efficient Video Sampling (EVS), it handles long-form videos while reducing inference cost.\n\nOpen-weights, training data, and fine-tuning recipes are released under a permissive NVIDIA open license, with deployment supported across NeMo, NIM, and major inference runtimes.","model_family":"Nemotron","model_family_id":41,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.2,"min_completion_price":0.6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL","prompt_price":0.2,"completion_price":0.6,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"stepfun/step-3.7-flash","object":"model","created":1626777600,"model_id":"stepfun/step-3.7-flash","canonical_slug":"stepfun/step-3.7-flash","display_name":"StepFun: Step 3.7 Flash","description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning.\n\nDesigned for coding, agentic workflows, structured outputs, and long-context productivity tasks.","model_family":"Step","model_family_id":81,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.2,"min_completion_price":1.15,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"stepfun","service_tier":"standard","endpoint_name":"step-3.7-flash","prompt_price":0.2,"completion_price":1.15,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-chat-v3.1","object":"model","created":1626777600,"model_id":"deepseek/deepseek-chat-v3.1","canonical_slug":"deepseek/deepseek-chat-v3.1","display_name":"Deepseek: Deepseek Chat V3.1","description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs\n\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.\n\nIt succeeds the DeepSeek V3-0324 model and performs well on a variety of tasks.","model_family":"DeepSeek","model_family_id":9,"model_version":"v3.1","category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.21,"min_completion_price":0.79,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"deepseek-ai/DeepSeek-V3.1","prompt_price":0.21,"completion_price":0.79,"context_length":163840,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-v3.1","object":"model","created":1626777600,"model_id":"deepseek/deepseek-v3.1","canonical_slug":"deepseek/deepseek-v3.1","display_name":"Deepseek: Deepseek V3.1","description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs\n\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.","model_family":"DeepSeek","model_family_id":9,"category_type":"LLM","context_length":131100,"max_input_tokens":131100,"max_output_tokens":131100,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.21,"min_completion_price":0.79,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"deepseek-ai/DeepSeek-V3.1","prompt_price":0.21,"completion_price":0.79,"context_length":163840,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"deepseek/deepseek-v3.1","prompt_price":0.27,"completion_price":1,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"siliconflow","service_tier":"standard","endpoint_name":"deepseek-ai/DeepSeek-V3.1","prompt_price":0.27,"completion_price":1,"context_length":164000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"deepseek-ai/DeepSeek-V3.1","prompt_price":0.3,"completion_price":0.95,"context_length":131070,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3.8-27b","object":"model","created":1626777600,"model_id":"qwen/qwen3.8-27b","canonical_slug":"qwen/qwen3.8-27b","display_name":"Qwen: Qwen3.8 27B","description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.212,"min_completion_price":0.848,"supported_endpoint_types":["openai"],"provider_count":3,"providers":[{"provider_slug":"alibaba/cn/flex","service_tier":"flex","endpoint_name":"qwen3.8-27b","prompt_price":0.212,"completion_price":0.848,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.8-27b","prompt_price":0.25,"completion_price":1.5,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"chutes","service_tier":"standard","endpoint_name":"Qwen/Qwen3.8-27B-TEE","prompt_price":0.4,"completion_price":3,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"z-ai/glm-4.7","object":"model","created":1626777600,"model_id":"z-ai/glm-4.7","canonical_slug":"z-ai/glm-4.7","display_name":"Z.AI: GLM 4.7","description":"GLM-4.7 is Z.AI’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.","model_family":"GLM","model_family_id":17,"model_version":"4.7","category_type":"LLM","context_length":200000,"max_input_tokens":200000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.2155,"min_completion_price":1.0035,"supported_endpoint_types":["openai"],"provider_count":9,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"glm-4.7","prompt_price":0.2155,"completion_price":1.0035,"context_length":198000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"zai-org/GLM-4.7","prompt_price":0.4,"completion_price":1.75,"context_length":202752,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"bigmodel","service_tier":"standard","endpoint_name":"glm-4.7","prompt_price":0.47,"completion_price":2.19,"context_length":200000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"zai-org/glm-4.7","prompt_price":0.52,"completion_price":1.75,"context_length":202750,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4.7","prompt_price":0.6,"completion_price":2.2,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"glm-4-7-251222","prompt_price":0.6,"completion_price":2.2,"context_length":200000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"zai-org/glm-4.7","prompt_price":0.6,"completion_price":2.2,"context_length":204800,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"baseten","service_tier":"standard","endpoint_name":"zai-org/GLM-4.7","prompt_price":0.6,"completion_price":2.2,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"cerebras","service_tier":"standard","endpoint_name":"zai-glm-4.7","prompt_price":2.25,"completion_price":2.75,"context_length":131000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"z-ai/glm-4.6","object":"model","created":1626777600,"model_id":"z-ai/glm-4.6","canonical_slug":"z-ai/glm-4.6","display_name":"Z.AI: GLM 4.6","description":"GLM-4.6 achieves comprehensive enhancements across multiple domains, including real-world coding, long-context processing, reasoning, searching, writing, and agentic applications. Details are as follows:\nLonger context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.\nSuperior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages.\nAdvanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.\nMore capable agents: GLM-4.6 exhibits stronger performance in tool use and search-based agents, and integrates more effectively within agent frameworks.\nRefined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.","model_family":"GLM","model_family_id":17,"model_version":"4.6","category_type":"LLM","context_length":202752,"max_input_tokens":202752,"max_output_tokens":131000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.2155,"min_completion_price":1.0035,"supported_endpoint_types":["openai"],"provider_count":3,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"glm-4.6","prompt_price":0.2155,"completion_price":1.0035,"context_length":198000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"zai-org/GLM-4.6","prompt_price":0.44,"completion_price":1.74,"context_length":202750,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4.6","prompt_price":0.6,"completion_price":2.2,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-coder-480b-a35b","object":"model","created":1626777600,"model_id":"qwen/qwen3-coder-480b-a35b","canonical_slug":"qwen/qwen3-coder-480b-a35b","display_name":"Qwen: Qwen3 Coder 480B A35B","description":"Qwen3-Coder-480B-A35B-Instruct is a cutting-edge open coding model from Qwen, matching Claude Sonnet’s performance in agentic programming, browser automation, and core development tasks. With native 256K context (extendable to 1M tokens via YaRN), it excels at repository-scale analysis and features specialized function-call support for platforms like Qwen Code and CLINE—making it ideal for complex, real-world development workflows.\n","model_family":"Qwen","model_family_id":49,"model_version":"3","category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.22,"min_completion_price":1,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"deepinfra/turbo","service_tier":"priority","endpoint_name":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","prompt_price":0.22,"completion_price":1,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow","quantization":"fp4"},{"provider_slug":"deepinfra/fp8","service_tier":"standard","endpoint_name":"Qwen/Qwen3-Coder-480B-A35B-Instruct","prompt_price":0.4,"completion_price":1.6,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow","quantization":"fp8"}]},{"id":"google/gemini-2.5-flash","object":"model","created":1626777600,"model_id":"google/gemini-2.5-flash","canonical_slug":"google/gemini-2.5-flash","display_name":"Google: Gemini 2.5 flash","description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.","model_family":"Gemini","model_family_id":15,"model_version":"2.5","category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"input_modalities":["Text","Code","Image","Audio","Video","PDF"],"output_modalities":["Text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.225,"min_completion_price":1.875,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-2.5-flash","prompt_price":0.225,"completion_price":1.875,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-2.5-flash","prompt_price":0.3,"completion_price":2.5,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-2.5-flash-preview-05-20","object":"model","created":1626777600,"model_id":"google/gemini-2.5-flash-preview-05-20","canonical_slug":"google/gemini-2.5-flash-preview-05-20","display_name":"Google: Gemini 2.5 flash preview 05 20","description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.","model_family":"Gemini","model_family_id":15,"model_version":"2.5","category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"input_modalities":["Text","Code","Image","Audio","Video","PDF"],"output_modalities":["Text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.225,"min_completion_price":1.875,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-2.5-flash","prompt_price":0.225,"completion_price":1.875,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-2.5-flash","prompt_price":0.3,"completion_price":2.5,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-2.5-flash-image-preview","object":"model","created":1626777600,"model_id":"google/gemini-2.5-flash-image-preview","canonical_slug":"google/gemini-2.5-flash-image-preview","display_name":"Google: Gemini 2.5 flash image preview","description":"Gemini 2.5 Flash Image Preview, AKA Nano Banana is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations.","model_family":"Gemini","model_family_id":15,"model_version":"2.5","category_type":"LLM","context_length":32800,"max_input_tokens":32800,"max_output_tokens":32800,"input_modalities":["Text","Image"],"output_modalities":["Text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.225,"min_completion_price":22.5,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-2.5-flash-image","prompt_price":0.225,"completion_price":22.5,"context_length":32800,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-2.5-flash-image","prompt_price":0.3,"completion_price":30,"context_length":32800,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-2.5-flash-image","object":"model","created":1626777600,"model_id":"google/gemini-2.5-flash-image","canonical_slug":"google/gemini-2.5-flash-image","display_name":"Google: Gemini 2.5 flash image","description":"Gemini 2.5 Flash Image, AKA Nano Banana is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations.","model_family":"Gemini","model_family_id":15,"model_version":"2.5","category_type":"LLM","context_length":32800,"max_input_tokens":32800,"max_output_tokens":32800,"input_modalities":["Text","Image"],"output_modalities":["Text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.225,"min_completion_price":22.5,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-2.5-flash-image","prompt_price":0.225,"completion_price":22.5,"context_length":32800,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-2.5-flash-image","prompt_price":0.3,"completion_price":30,"context_length":32800,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-2.5-flash-preview","object":"model","created":1626777600,"model_id":"google/gemini-2.5-flash-preview","canonical_slug":"google/gemini-2.5-flash-preview","display_name":"Google: Gemini 2.5 flash preview","description":"Gemini 2.5 Flash is our best model in terms of price and performance, and offers well-rounded capabilities. Gemini 2.5 Flash is our first Flash model model that features thinking capabilities, which lets you see the thinking process that the model goes through when generating its response.","model_family":"Gemini","model_family_id":15,"model_version":"2.5","category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"input_modalities":["Text","Code","Image","Audio","Video","PDF"],"output_modalities":["Text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.225,"min_completion_price":1.875,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-2.5-flash","prompt_price":0.225,"completion_price":1.875,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-2.5-flash","prompt_price":0.3,"completion_price":2.5,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"apodex/apodex-1.1","object":"model","created":1626777600,"model_id":"apodex/apodex-1.1","canonical_slug":"apodex/apodex-1.1","display_name":"Apodex 1.1","description":"Apodex's 397B flagship core reasoning model.","model_family":"Apodex","model_family_id":119,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.24,"min_completion_price":2.4,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"apodex","service_tier":"standard","endpoint_name":"apodex-1.1","prompt_price":0.24,"completion_price":2.4,"context_length":256000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"mistral/mistral-24b-venice-edition","object":"model","created":1626777600,"model_id":"mistral/mistral-24b-venice-edition","canonical_slug":"mistral/mistral-24b-venice-edition","display_name":"Dolphin Mistral 24B Uncensored","description":"Dolphin's uncensored fine-tune of Mistral Small 24B (fp16), built for open-ended roleplay, creative writing and unfiltered dialogue. Vision (up to 10 images), tool calling, structured output.\n\n    The dphn model card identifies Dolphin Mistral 24B Venice Edition as a collaboration with Venice, based on Mistral Small 24B Instruct 2501, intended for steerable general-purpose dialogue and creative work. The card labels text generation; vision is a Unlid hosting declaration, not an independently tested checkpoint capability.\n\n    Unlid declares a 128,000-token context and up to 8,192 output tokens. Input: text, image; output: text. Tool calling is supported. No reasoning mode is declared in the structured catalog. Reasoning tokens, when generated, count toward the output budget and are charged as output. Prices are USD per million tokens from the live catalog; missing cache discounts use the normal input price under Unlid billing rules. Limits and capabilities are provider declarations, not results of an inference test.","model_family":"Mistral","model_family_id":37,"category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":8192,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.24,"min_completion_price":1.08,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"unlid","service_tier":"standard","endpoint_name":"dolphin-mistral-24b-uncensored","prompt_price":0.24,"completion_price":1.08,"context_length":128000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"}]},{"id":"bytedance/seed-1.8","object":"model","created":1626777600,"model_id":"bytedance/seed-1.8","canonical_slug":"bytedance/seed-1.8","display_name":"ByteDance: Seed 1.8","description":"A brand-new model optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.\n\n","model_family":"Seed","model_family_id":51,"model_version":"1.8","category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":64000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.25,"min_completion_price":2,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260303105613-99lm2","prompt_price":0.25,"completion_price":2,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"byteplus/preset","service_tier":"standard","endpoint_name":"seed-1-8-251228","prompt_price":0.25,"completion_price":2,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seed-1.6","object":"model","created":1626777600,"model_id":"bytedance/seed-1.6","canonical_slug":"bytedance/seed-1.6","display_name":"ByteDance: Seed 1.6","description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.","model_family":"Seed","model_family_id":51,"model_version":"1.6","category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32800,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.25,"min_completion_price":2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"seed-1-6-250915","prompt_price":0.25,"completion_price":2,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-omni-30b-a3b-instruct","object":"model","created":1626777600,"model_id":"qwen/qwen3-omni-30b-a3b-instruct","canonical_slug":"qwen/qwen3-omni-30b-a3b-instruct","display_name":"Qwen: Qwen3 Omni 30B A3b Instruct","description":"The Qwen-Omni model accepts combined inputs of text and a single additional modality (image, audio, or video) to generate responses in text or speech. It offers a variety of human-like voices, supports speech output in multiple languages and dialects, and is suitable for applications such as text creation, visual recognition, and voice assistants\n","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":65536,"max_input_tokens":65536,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.25,"min_completion_price":0.97,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"novita","service_tier":"standard","endpoint_name":"qwen/qwen3-omni-30b-a3b-instruct","prompt_price":0.25,"completion_price":0.97,"context_length":65536,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-omni-30b-a3b-thinking","object":"model","created":1626777600,"model_id":"qwen/qwen3-omni-30b-a3b-thinking","canonical_slug":"qwen/qwen3-omni-30b-a3b-thinking","display_name":"Qwen: Qwen3 Omni 30b A3b Thinking","description":"The Qwen-Omni model accepts combined inputs of text and a single additional modality (image, audio, or video) to generate responses in text or speech. It offers a variety of human-like voices, supports speech output in multiple languages and dialects, and is suitable for applications such as text creation, visual recognition, and voice assistants\n","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":65536,"max_input_tokens":65536,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.25,"min_completion_price":0.97,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"novita","service_tier":"standard","endpoint_name":"qwen/qwen3-omni-30b-a3b-thinking","prompt_price":0.25,"completion_price":0.97,"context_length":65536,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen-mt-plus","object":"model","created":1626777600,"model_id":"qwen/qwen-mt-plus","canonical_slug":"qwen/qwen-mt-plus","display_name":"Qwen: Qwen Mt Plus","description":"Qwen-MT is a large language model optimized for machine translation, built upon the foundation of the Tongyi Qianwen model. It supports translation across 92 languages — including Chinese, English, Japanese, Korean, French, Spanish, German, Thai, Indonesian, Vietnamese, Arabic, and more — enabling seamless multilingual communication.\n","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":16384,"max_input_tokens":16384,"max_output_tokens":8192,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.25,"min_completion_price":0.75,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"novita","service_tier":"standard","endpoint_name":"qwen/qwen-mt-plus","prompt_price":0.25,"completion_price":0.75,"context_length":16384,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen-plus-character","object":"model","created":1626777600,"model_id":"qwen/qwen-plus-character","canonical_slug":"qwen/qwen-plus-character","display_name":"Qwen: Qwen Plus Character","description":"The Thousand Questions series of role-playing models is a dynamically updated version. Model updates will be announced in advance. It is suitable for anthropomorphic role-playing and has optimized the ability to follow limited character instructions, advance topics, listen and empathize, etc., supporting in-depth reproduction of personalized characters.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":32000,"max_input_tokens":32000,"max_output_tokens":4000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.25,"min_completion_price":0.7,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen-plus-character","prompt_price":0.25,"completion_price":0.7,"context_length":32000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"infron/auto","object":"model","created":1626777600,"model_id":"infron/auto","canonical_slug":"infron/auto","display_name":"Auto Router (Beta)","description":"The Auto Router automatically selects the best model for your prompt. It routes you based on the kind of task your prompt represents.\n\nMulti-turn conversations stick to one model until it is no longer a leading choice for your task.","model_family":"SEAR","model_family_id":120,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","video","audio","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.25,"min_completion_price":1.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"infron/us","service_tier":"standard","endpoint_name":"infron/auto","prompt_price":0.25,"completion_price":1.5,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"hcompany/holo3-1-35b-a3b","object":"model","created":1626777600,"model_id":"hcompany/holo3-1-35b-a3b","canonical_slug":"hcompany/holo3-1-35b-a3b","display_name":"Holo: Holo3.1 35B A3B","description":"Holo3.1 35B (3B active) vision-language model optimized for GUI agents and computer use.","model_family":"Holo","model_family_id":69,"category_type":"LLM","context_length":65537,"max_input_tokens":65537,"max_output_tokens":8192,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.25,"min_completion_price":1.8,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"hcompany","service_tier":"standard","endpoint_name":"holo3-1-35b-a3b","prompt_price":0.25,"completion_price":1.8,"context_length":65537,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"minimax/minimax-m2","object":"model","created":1626777600,"model_id":"minimax/minimax-m2","canonical_slug":"minimax/minimax-m2","display_name":"MiniMax: MiniMax M2","description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency.\n\nThe model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors.","model_family":"MiniMax","model_family_id":36,"model_version":"2","category_type":"LLM","context_length":200000,"max_input_tokens":200000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.255,"min_completion_price":1,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"MiniMaxAI/MiniMax-M2","prompt_price":0.255,"completion_price":1,"context_length":196610,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"minimax","service_tier":"standard","endpoint_name":"MiniMax-M2","prompt_price":0.3,"completion_price":1.2,"context_length":200000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-chat","object":"model","created":1626777600,"model_id":"deepseek/deepseek-chat","canonical_slug":"deepseek/deepseek-chat","display_name":"Deepseek: Deepseek Chat","description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.","model_family":"DeepSeek","model_family_id":9,"model_version":"3","category_type":"LLM","context_length":163840,"max_input_tokens":163840,"max_output_tokens":163840,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.26,"min_completion_price":0.38,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"deepseek-ai/DeepSeek-V3.2","prompt_price":0.26,"completion_price":0.38,"context_length":163840,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"minimax/minimax-m2.1","object":"model","created":1626777600,"model_id":"minimax/minimax-m2.1","canonical_slug":"minimax/minimax-m2.1","display_name":"MiniMax: Minimax M2.1","description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency.\n\nCompared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance.","model_family":"MiniMax","model_family_id":36,"model_version":"2.1","category_type":"LLM","context_length":204800,"max_input_tokens":204800,"max_output_tokens":131000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.27,"min_completion_price":0.95,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"MiniMaxAI/MiniMax-M2.1","prompt_price":0.27,"completion_price":0.95,"context_length":196608,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"minimaxai/minimax-m2.1","prompt_price":0.29,"completion_price":0.95,"context_length":196610,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"minimax","service_tier":"standard","endpoint_name":"minimax-m2.1","prompt_price":0.3,"completion_price":1.2,"context_length":204800,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"minimax/minimax-m2.1","prompt_price":0.3,"completion_price":1.2,"context_length":204800,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-v3.1-terminus","object":"model","created":1626777600,"model_id":"deepseek/deepseek-v3.1-terminus","canonical_slug":"deepseek/deepseek-v3.1-terminus","display_name":"Deepseek: Deepseek V3.1 Terminus","description":"DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs\n\nThe model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.","model_family":"DeepSeek","model_family_id":9,"model_version":"v3.1","category_type":"LLM","context_length":163840,"max_input_tokens":163840,"max_output_tokens":163840,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.27,"min_completion_price":0.95,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"deepseek-ai/DeepSeek-V3.1-Terminus","prompt_price":0.27,"completion_price":0.95,"context_length":163840,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"deepseek-ai/DeepSeek-V3.1-Terminus","prompt_price":0.3,"completion_price":0.95,"context_length":131070,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"minimax/minimax-m3","object":"model","created":1626777600,"model_id":"minimax/minimax-m3","canonical_slug":"minimax/minimax-m3","display_name":"MiniMax: MiniMax M3","description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding, and tool use. It is built on MiniMax Sparse Attention (MSA), which replaces full attention with KV-block selection to cut per-token compute at long context — roughly 1/20 the cost of the previous generation at 1M tokens, with substantially faster prefill and decode while retaining quality across most tasks.\n\nTrained as a native multimodal model on interleaved data and tuned for multi-turn, production-like collaboration via an interactive user-simulator framework, the model is oriented toward sustained, multi-step tasks rather than single-turn execution.","model_family":"MiniMax","model_family_id":36,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":131100,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.28,"min_completion_price":1.1,"supported_endpoint_types":["openai"],"provider_count":7,"providers":[{"provider_slug":"lilac","service_tier":"flex","endpoint_name":"minimaxai/minimax-m3","prompt_price":0.28,"completion_price":1.1,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"minimax","service_tier":"standard","endpoint_name":"MiniMax-M3","prompt_price":0.3,"completion_price":1.2,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"MiniMaxAI/MiniMax-M3","prompt_price":0.3,"completion_price":1.2,"context_length":524288,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"minimax/minimax-m3","prompt_price":0.3,"completion_price":1.2,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"fireworks","service_tier":"standard","endpoint_name":"accounts/fireworks/models/minimax-m3","prompt_price":0.3,"completion_price":1.2,"context_length":512000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"minimaxai/minimax-m3","prompt_price":0.3,"completion_price":1.2,"context_length":524300,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"together","service_tier":"standard","endpoint_name":"MiniMaxAI/MiniMax-M3","prompt_price":0.3,"completion_price":1.2,"context_length":524300,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-3.6-flash","object":"model","created":1626777600,"model_id":"google/gemini-3.6-flash","canonical_slug":"google/gemini-3.6-flash","display_name":"Google: Gemini 3.6 Flash","description":"Gemini 3.6 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs.\n\nDefaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.","model_family":"Gemini","model_family_id":15,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.28125,"min_completion_price":1.40625,"supported_endpoint_types":["gemini","openai"],"provider_count":3,"providers":[{"provider_slug":"google-vertex/flex","service_tier":"flex","endpoint_name":"gemini-3.6-flash","prompt_price":0.28125,"completion_price":1.40625,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3.6-flash","prompt_price":0.5625,"completion_price":2.8125,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex/priority","service_tier":"priority","endpoint_name":"gemini-3.6-flash","prompt_price":1.0125,"completion_price":5.0625,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-3.7-flash","object":"model","created":1626777600,"model_id":"google/gemini-3.7-flash","canonical_slug":"google/gemini-3.7-flash","display_name":"Google: Gemini 3.7 Flash","description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.","model_family":"Gemini","model_family_id":15,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.28125,"min_completion_price":1.40625,"supported_endpoint_types":["gemini","openai"],"provider_count":3,"providers":[{"provider_slug":"google-vertex/flex","service_tier":"flex","endpoint_name":"gemini-3.7-flash","prompt_price":0.28125,"completion_price":1.40625,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3.7-flash","prompt_price":0.5625,"completion_price":2.8125,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex/priority","service_tier":"priority","endpoint_name":"gemini-3.7-flash","prompt_price":1.0125,"completion_price":5.0625,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-3.8-flash","object":"model","created":1626777600,"model_id":"google/gemini-3.8-flash","canonical_slug":"google/gemini-3.8-flash","display_name":"Google: Gemini 3.8 Flash","description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.\n\n","model_family":"Gemini","model_family_id":15,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.28125,"min_completion_price":1.40625,"supported_endpoint_types":["gemini","openai"],"provider_count":3,"providers":[{"provider_slug":"google-vertex/flex","service_tier":"flex","endpoint_name":"gemini-3.8-flash","prompt_price":0.28125,"completion_price":1.40625,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3.8-flash","prompt_price":0.5625,"completion_price":2.8125,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex/priority","service_tier":"priority","endpoint_name":"gemini-3.8-flash","prompt_price":1.0125,"completion_price":5.0625,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-5","object":"model","created":1626777600,"model_id":"z-ai/glm-5","canonical_slug":"z-ai/glm-5","display_name":"Z.AI: GLM 5","description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.","model_family":"GLM","model_family_id":17,"model_version":"5","category_type":"LLM","context_length":202752,"max_input_tokens":202752,"max_output_tokens":202752,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.2865,"min_completion_price":1.29,"supported_endpoint_types":["openai"],"provider_count":8,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"glm-5","prompt_price":0.2865,"completion_price":1.29,"context_length":198000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"zai-org/GLM-5","prompt_price":0.6,"completion_price":2.08,"context_length":202752,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"},{"provider_slug":"gmicloud","service_tier":"standard","endpoint_name":"zai-org/GLM-5-FP8","prompt_price":0.6,"completion_price":1.92,"context_length":202752,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"bigmodel","service_tier":"standard","endpoint_name":"glm-5","prompt_price":0.63,"completion_price":2.82,"context_length":202805,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"chutes","service_tier":"standard","endpoint_name":"zai-org/GLM-5-TEE","prompt_price":0.95,"completion_price":2.55,"context_length":202750,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"zai-org/glm-5","prompt_price":0.95,"completion_price":3.15,"context_length":202750,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-5","prompt_price":1,"completion_price":3.2,"context_length":202805,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"zai-org/glm-5","prompt_price":1,"completion_price":3.2,"context_length":202800,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"moonshotai/kimi-k2.5","object":"model","created":1626777600,"model_id":"moonshotai/kimi-k2.5","canonical_slug":"moonshotai/kimi-k2.5","display_name":"Moonshot: Kimi K2.5","description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.","model_family":"Kimi","model_family_id":27,"model_version":"2.5","category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.287,"min_completion_price":1.5055,"supported_endpoint_types":["openai"],"provider_count":7,"providers":[{"provider_slug":"alibaba/cn/flex","service_tier":"flex","endpoint_name":"kimi-k2.5","prompt_price":0.287,"completion_price":1.5055,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"chutes","service_tier":"standard","endpoint_name":"moonshotai/Kimi-K2.5-TEE","prompt_price":0.44,"completion_price":2,"context_length":262140,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int4"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"moonshotai/Kimi-K2.5","prompt_price":0.45,"completion_price":2.25,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"moonshotai/kimi-k2.5","prompt_price":0.5,"completion_price":2.6,"context_length":262140,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow","quantization":"int4"},{"provider_slug":"moonshotai","service_tier":"standard","endpoint_name":"kimi-k2.5","prompt_price":0.6,"completion_price":3,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int4"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"moonshotai/kimi-k2.5","prompt_price":0.6,"completion_price":3,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"gmicloud","service_tier":"standard","endpoint_name":"moonshotai/Kimi-K2.5","prompt_price":0.6,"completion_price":3,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"nousresearch/hermes-3-llama-3.1-70b","object":"model","created":1626777600,"model_id":"nousresearch/hermes-3-llama-3.1-70b","canonical_slug":"nousresearch/hermes-3-llama-3.1-70b","display_name":"Nous: Hermes 3 Llama 3.1 70B","description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.\n\nHermes 3 70B is a competitive, if not superior finetune of the Llama-3.1 70B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.\n\nThe Hermes 3 series builds and expands on the Hermes 2 set of capabilities, including more powerful and reliable function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills.","model_family":"Nous","model_family_id":42,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.3,"min_completion_price":0.3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"NousResearch/Hermes-3-Llama-3.1-70B","prompt_price":0.3,"completion_price":0.3,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"z-ai/glm-4.6v","object":"model","created":1626777600,"model_id":"z-ai/glm-4.6v","canonical_slug":"z-ai/glm-4.6v","display_name":"Z.AI: GLM 4.6V","description":"GLM-4.6 achieves comprehensive enhancements across multiple domains, including real-world coding, long-context processing, reasoning, searching, writing, and agentic applications. Details are as follows:\nLonger context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks.\nSuperior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages.\nAdvanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability.\nMore capable agents: GLM-4.6 exhibits stronger performance in tool use and search-based agents, and integrates more effectively within agent frameworks.\nRefined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.","model_family":"GLM","model_family_id":17,"model_version":"4.6v","category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.3,"min_completion_price":0.9,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4.6v","prompt_price":0.3,"completion_price":0.9,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"kwaipilot/kat-coder-pro","object":"model","created":1626777600,"model_id":"kwaipilot/kat-coder-pro","canonical_slug":"kwaipilot/kat-coder-pro","display_name":"Kwaipilot: KAT-Coder-Pro V1","description":"KAT-Coder-Pro V1 is KwaiKAT's most advanced agentic coding model in the KAT-Coder series. Designed specifically for agentic coding tasks, it excels in real-world software engineering scenarios, achieving 73.4% solve rate on the SWE-Bench Verified benchmark.\n\nThe model has been optimized for tool-use capability, multi-turn interaction, instruction following, generalization, and comprehensive capabilities through a multi-stage training process, including mid-training, supervised fine-tuning (SFT), reinforcement fine-tuning (RFT), and scalable agentic RL.","model_family":"Kwaipilot","model_family_id":73,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.3,"min_completion_price":1.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"kwaipilot/kat-coder-pro-v1","prompt_price":0.3,"completion_price":1.2,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"minimax/minimax-m2-her","object":"model","created":1626777600,"model_id":"minimax/minimax-m2-her","canonical_slug":"minimax/minimax-m2-her","display_name":"MiniMax: MiniMax M2-her","description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message roles (user_system, group, sample_message_user, sample_message_ai) and can learn from example dialogue to better match the style and pacing of your scenario, making it a strong choice for storytelling, companions, and conversational experiences where natural flow and vivid interaction matter most.","model_family":"MiniMax","model_family_id":36,"category_type":"LLM","context_length":65536,"max_input_tokens":65536,"max_output_tokens":2000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.3,"min_completion_price":1.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"minimax","service_tier":"standard","endpoint_name":"M2-her","prompt_price":0.3,"completion_price":1.2,"context_length":65536,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"amazon/nova-2-lite-v1","object":"model","created":1626777600,"model_id":"amazon/nova-2-lite-v1","canonical_slug":"amazon/nova-2-lite-v1","display_name":"Amazon: Nova 2 Lite","description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text.\n\nNova 2 Lite demonstrates standout capabilities in processing documents, extracting information from videos, generating code, providing accurate grounded answers, and automating multi-step agentic workflows.","model_family":"Nova","model_family_id":76,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":65500,"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.3,"min_completion_price":2.5,"supported_endpoint_types":["anthropic","openai"],"provider_count":1,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.amazon.nova-2-lite-v1","prompt_price":0.3,"completion_price":2.5,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"hcompany/holo4-35b-a3b","object":"model","created":1626777600,"model_id":"hcompany/holo4-35b-a3b","canonical_slug":"hcompany/holo4-35b-a3b","display_name":"Holo: Holo4 35B A3B","description":"Holo4 35B (3B active) vision-language model optimized for GUI agents and computer use.","model_family":"Holo","model_family_id":69,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.3,"min_completion_price":2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"hcompany","service_tier":"standard","endpoint_name":"holo4-35b-a3b","prompt_price":0.3,"completion_price":2,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"z-ai/glm-5.3","object":"model","created":1626777600,"model_id":"z-ai/glm-5.3","canonical_slug":"z-ai/glm-5.3","display_name":"Z.AI: GLM 5.3","description":"GLM-5.3 is an advanced large language model designed to deliver strong performance across a wide range of natural language processing tasks, including text generation, reasoning, summarization, translation, coding assistance, and conversational interaction. Built on the GLM architecture, it aims to provide more accurate understanding, more coherent responses, and improved instruction-following capabilities. With enhanced contextual comprehension and multilingual support, GLM-5.3 can be applied in education, business, research, software development, and intelligent assistant scenarios, offering users an efficient and flexible AI-powered solution for complex language tasks.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":1024000,"max_input_tokens":1024000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.3393,"min_completion_price":1.1871,"supported_endpoint_types":["openai"],"provider_count":7,"providers":[{"provider_slug":"alibaba/cn","service_tier":"flex","endpoint_name":"glm-5.3","prompt_price":0.3393,"completion_price":1.1871,"context_length":1024000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"glm-5.3","prompt_price":0.5655,"completion_price":1.9785,"context_length":1024000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/hk","service_tier":"standard","endpoint_name":"glm-5.3","prompt_price":0.5655,"completion_price":1.9785,"context_length":1024000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"glm-5.3","prompt_price":0.5655,"completion_price":1.9785,"context_length":1024000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/jp","service_tier":"standard","endpoint_name":"glm-5.3","prompt_price":0.5655,"completion_price":1.9785,"context_length":1024000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"glm-5.3","prompt_price":0.7,"completion_price":2.2,"context_length":1024000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-5.3","prompt_price":1.4,"completion_price":4.4,"context_length":1024000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"qwen/qwen3-235b-a22b","object":"model","created":1626777600,"model_id":"qwen/qwen3-235b-a22b","canonical_slug":"qwen/qwen3-235b-a22b","display_name":"Qwen: Qwen3 235B A22B","description":"Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a \"thinking\" mode for complex reasoning, math, and code tasks, and a \"non-thinking\" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":40960,"max_input_tokens":40960,"max_output_tokens":32768,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.35,"min_completion_price":1.4,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-235b-a22b","prompt_price":0.35,"completion_price":1.4,"context_length":131100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"}]},{"id":"meta-ai/muse-glimmer-30b","object":"model","created":1626777600,"model_id":"meta-ai/muse-glimmer-30b","canonical_slug":"meta-ai/muse-glimmer-30b","display_name":"Meta AI: Muse Glimmer 30B","description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon agentic and coding workflows, with multi-step reasoning, reliable tool use, failure recovery, image understanding, and multilingual support across more than 100 languages.","model_family":"Muse","model_family_id":113,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.35,"min_completion_price":1.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"together","service_tier":"standard","endpoint_name":"meta-models/Muse-Glimmer-30B","prompt_price":0.35,"completion_price":1.5,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-5.3-flashx","object":"model","created":1626777600,"model_id":"z-ai/glm-5.3-flashx","canonical_slug":"z-ai/glm-5.3-flashx","display_name":"Z.AI: GLM 5.3 FlashX","description":"GLM-5.3-FlashX is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.37,"min_completion_price":1.25,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-5.3-flashx","prompt_price":0.37,"completion_price":1.25,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"bytedance/sc-250615","object":"model","created":1626777600,"model_id":"bytedance/sc-250615","canonical_slug":"bytedance/sc-250615","display_name":"ByteDance: Skylark Pro SC 250615","description":"Roleplay model based on Skylark Pro.","model_family":"ByteDance","model_family_id":63,"category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":12000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.4,"min_completion_price":1.6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20251201141801-7twn8","prompt_price":0.4,"completion_price":1.6,"context_length":128000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"meta-llama/llama-3.1-70b-instruct","object":"model","created":1626777600,"model_id":"meta-llama/llama-3.1-70b-instruct","canonical_slug":"meta-llama/llama-3.1-70b-instruct","display_name":"Meta: Llama 3.1 70B Instruct","description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes \u0026 flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases.\n\nIt has demonstrated strong performance compared to leading closed-source models in human evaluations.","model_family":"Llama","model_family_id":31,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.4,"min_completion_price":0.4,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"meta-llama/Meta-Llama-3.1-70B-Instruct","prompt_price":0.4,"completion_price":0.4,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"}]},{"id":"hcompany/holo4-27b","object":"model","created":1626777600,"model_id":"hcompany/holo4-27b","canonical_slug":"hcompany/holo4-27b","display_name":"Holo: Holo4 27B","description":"Holo4 27B (Dense) vision-language model optimized for GUI agents and computer use.","model_family":"Holo","model_family_id":69,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16384,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.4,"min_completion_price":3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"hcompany","service_tier":"standard","endpoint_name":"holo4-27b","prompt_price":0.4,"completion_price":3,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"hcompany/holo3-122b-a10b","object":"model","created":1626777600,"model_id":"hcompany/holo3-122b-a10b","canonical_slug":"hcompany/holo3-122b-a10b","display_name":"Holo: Holo3 122B A10B","description":"Holo3 122B (10B active) vision-language model optimized for GUI agents and computer use.","model_family":"Holo","model_family_id":69,"category_type":"LLM","context_length":65537,"max_input_tokens":65537,"max_output_tokens":8192,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.4,"min_completion_price":3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"hcompany","service_tier":"standard","endpoint_name":"holo3-122b-a10b","prompt_price":0.4,"completion_price":3,"context_length":65537,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"xiaomi/mimo-v2.6-pro","object":"model","created":1626777600,"model_id":"xiaomi/mimo-v2.6-pro","canonical_slug":"xiaomi/mimo-v2.6-pro","display_name":"Xiaomi: Mimo V2.6 Pro","description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding workloads. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers top-tier performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.","model_family":"MiMo","model_family_id":35,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.435,"min_completion_price":0.87,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xiaomi","service_tier":"standard","endpoint_name":"mimo-v2.6-pro","prompt_price":0.435,"completion_price":0.87,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-v4-flash-vision-exp","object":"model","created":1626777600,"model_id":"deepseek/deepseek-v4-flash-vision-exp","canonical_slug":"deepseek/deepseek-v4-flash-vision-exp","display_name":"DeepSeek: DeepSeek V4 Flash Vision Experimental","description":"The deepseek-v4-flash-vision-exp model accepts images alongside text, so you can ask the model to describe pictures, read text from screenshots, analyze charts, and more.\n\nSupported image formats: JPEG, PNG, GIF, and WebP. The format is detected from the actual file content, not from the file name or the declared MIME type.","model_family":"DeepSeek","model_family_id":9,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":384000,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.44,"min_completion_price":1.32,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepseek","service_tier":"standard","endpoint_name":"deepseek-v4-flash-vision-exp","prompt_price":0.44,"completion_price":1.32,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"moonshotai/kimi-k2.7-code","object":"model","created":1626777600,"model_id":"moonshotai/kimi-k2.7-code","canonical_slug":"moonshotai/kimi-k2.7-code","display_name":"Moonshot: Kimi K2.7 Code","description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts architecture that accepts text, image and video input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 256K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.","model_family":"Kimi","model_family_id":27,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.44695,"min_completion_price":1.85655,"supported_endpoint_types":["openai"],"provider_count":12,"providers":[{"provider_slug":"alibaba/cn/flex","service_tier":"flex","endpoint_name":"kimi-k2.7-code","prompt_price":0.44695,"completion_price":1.85655,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"kimi-k2.7-code","prompt_price":0.44695,"completion_price":1.85655,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/hk","service_tier":"standard","endpoint_name":"kimi-k2.7-code","prompt_price":0.44695,"completion_price":1.85655,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"kimi-k2.7-code","prompt_price":0.44695,"completion_price":1.85655,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"kimi-k2.7-code","prompt_price":0.475,"completion_price":2,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"moonshotai/Kimi-K2.7-Code","prompt_price":0.74,"completion_price":3.5,"context_length":256000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"},{"provider_slug":"inceptron","service_tier":"standard","endpoint_name":"moonshotai/Kimi-K2.7-Code","prompt_price":0.75,"completion_price":3.15,"context_length":256000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int4"},{"provider_slug":"siliconflow","service_tier":"standard","endpoint_name":"moonshotai/Kimi-K2.7-Code","prompt_price":0.94,"completion_price":4,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"moonshotai","service_tier":"standard","endpoint_name":"kimi-k2.7-code","prompt_price":0.95,"completion_price":4,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int4"},{"provider_slug":"novita","service_tier":"standard","endpoint_name":"moonshotai/kimi-k2.7-code","prompt_price":0.95,"completion_price":4,"context_length":256000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"moonshotai/kimi-k2.7-code","prompt_price":0.95,"completion_price":4,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"makora","service_tier":"flex","endpoint_name":"moonshotai/Kimi-K2.7-Code","prompt_price":0.9701,"completion_price":3.865,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemma-4-26b-a4b-it-uncensored","object":"model","created":1626777600,"model_id":"google/gemma-4-26b-a4b-it-uncensored","canonical_slug":"google/gemma-4-26b-a4b-it-uncensored","display_name":"Gemma 4 26B A4B Uncensored","description":"Community uncensored build of Google Gemma 4 26B A4B instruct (26B total, 4B active): refusals removed from the weights, vision and tool calling kept. Answers directly, without a thinking phase.\n\n    TrevorJS's card describes norm-preserving edits to dense pathways and expert-specific edits to the mixture-of-experts layers of Gemma 4 26B A4B. The hosted endpoint currently answers without a thinking phase because of the upstream reasoning-output parser limitation; its model family does not imply every base-model modality is exposed.\n\n    Unlid declares a 32,768-token context and up to 32,768 output tokens. Input: text, image; output: text. Tool calling is supported. No reasoning mode is declared in the structured catalog. Reasoning tokens, when generated, count toward the output budget and are charged as output. Prices are USD per million tokens from the live catalog; missing cache discounts use the normal input price under Unlid billing rules. Limits and capabilities are provider declarations, not results of an inference test.","model_family":"Gemma","model_family_id":16,"category_type":"LLM","context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.48,"min_completion_price":0.96,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"unlid","service_tier":"standard","endpoint_name":"gemma-4-26b-a4b-it-uncensored","prompt_price":0.48,"completion_price":0.96,"context_length":32768,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3-coder-plus","object":"model","created":1626777600,"model_id":"qwen/qwen3-coder-plus","canonical_slug":"qwen/qwen3-coder-plus","display_name":"Qwen: Qwen3 Coder Plus","description":"Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and environment interaction, combining coding proficiency with versatile general-purpose abilities.\n\n","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":128000,"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.5,"min_completion_price":2.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-coder-plus","prompt_price":0.5,"completion_price":2.5,"context_length":131100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"int8"}]},{"id":"deepseek/deepseek-r1","object":"model","created":1626777600,"model_id":"deepseek/deepseek-r1","canonical_slug":"deepseek/deepseek-r1","display_name":"Deepseek: Deepseek R1","description":"DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.\n\nMIT licensed: Distill \u0026 commercialize freely!","model_family":"DeepSeek","model_family_id":9,"model_version":"r1","category_type":"LLM","context_length":163840,"max_input_tokens":163840,"max_output_tokens":163840,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.5,"min_completion_price":2.15,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"deepseek-ai/DeepSeek-R1-0528","prompt_price":0.5,"completion_price":2.15,"context_length":163840,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-r1-0528","object":"model","created":1626777600,"model_id":"deepseek/deepseek-r1-0528","canonical_slug":"deepseek/deepseek-r1-0528","display_name":"Deepseek: Deepseek R1 0528","description":"May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.\n\nFully open-source model.","model_family":"DeepSeek","model_family_id":9,"model_version":"r1","category_type":"LLM","context_length":163840,"max_input_tokens":163840,"max_output_tokens":163840,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.5,"min_completion_price":2.15,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"deepseek-ai/DeepSeek-R1-0528","prompt_price":0.5,"completion_price":2.15,"context_length":163840,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"deepseek-ai/deepseek-r1-0528","prompt_price":0.55,"completion_price":2.15,"context_length":131070,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"volcengine/doubao-seed-2.0-code","object":"model","created":1626777600,"model_id":"volcengine/doubao-seed-2.0-code","canonical_slug":"volcengine/doubao-seed-2.0-code","display_name":"VolcanoEngine: Doubao-Seed 2.0 Code","description":"This coding model is optimized for real-world programming environments and can reliably call tools in common IDEs such as Claude Code. The model is specifically optimized for front-end capabilities, delivering excellent performance when using common front-end frameworks. The model supports the use of Skills and can be used in conjunction with various custom skills.","model_family":"Doubao-Seed","model_family_id":66,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.5,"min_completion_price":2.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"volcengine","service_tier":"standard","endpoint_name":"ep-20260320164304-5fvfd","prompt_price":0.5,"completion_price":2.5,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"volcengine/doubao-seed-2.0-pro","object":"model","created":1626777600,"model_id":"volcengine/doubao-seed-2.0-pro","canonical_slug":"volcengine/doubao-seed-2.0-pro","display_name":"VolcanoEngine: Doubao-Seed 2.0 Pro","description":"A flagship-level, all-around general-purpose model designed for complex reasoning and long-chain task execution scenarios in the Agent era. It emphasizes multimodal understanding, long-context reasoning, structured generation, and tool-enhanced execution. Its outstanding capabilities in executing complex instructions and multiple constraints enable it to reliably handle scenarios such as multi-step complex planning, complex graph and text reasoning, video content understanding, and highly complex analysis.","model_family":"Doubao-Seed","model_family_id":66,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.5,"min_completion_price":2.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"volcengine","service_tier":"standard","endpoint_name":"ep-20260320164102-mrf57","prompt_price":0.5,"completion_price":2.5,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"nvidia/nemotron-3-ultra-550b-a55b","object":"model","created":1626777600,"model_id":"nvidia/nemotron-3-ultra-550b-a55b","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b","display_name":"NVIDIA: Nemotron 3 Ultra","description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.","model_family":"Nemotron","model_family_id":41,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":16400,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.5,"min_completion_price":2.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","prompt_price":0.5,"completion_price":2.5,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"}]},{"id":"bytedance/seed-2.0-code","object":"model","created":1626777600,"model_id":"bytedance/seed-2.0-code","canonical_slug":"bytedance/seed-2.0-code","display_name":"ByteDance: Seed 2.0 Code","description":"A coding model optimized for real-world development environments, with reliable tool use in common IDEs such as Claude Code. It delivers strong front-end performance and supports Skills.","model_family":"Seed","model_family_id":51,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":128000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.5,"min_completion_price":3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260623083628-ld5np","prompt_price":0.5,"completion_price":3,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"bytedance/seed-2.1-turbo","object":"model","created":1626777600,"model_id":"bytedance/seed-2.1-turbo","canonical_slug":"bytedance/seed-2.1-turbo","display_name":"ByteDance: Seed 2.1 Turbo","description":"A next-generation model tailored for the coding and agent era.","model_family":"Seed","model_family_id":51,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.5,"min_completion_price":2.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260715170126-6bbhr","prompt_price":0.5,"completion_price":2.5,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.8-27b-abliterated-cyber","object":"model","created":1626777600,"model_id":"qwen/qwen3.8-27b-abliterated-cyber","canonical_slug":"qwen/qwen3.8-27b-abliterated-cyber","display_name":"Qwen: Qwen3.8 27B Abliterated Cyber","description":"Qwen3.8-27B Abliterated Cyber is a cybersecurity-focused variant of Qwen3.8-27B, optimized for security research, code analysis, penetration-testing workflows, and agentic tool use. It is designed to provide direct, low-refusal responses while retaining strong reasoning, coding, and structured tool-calling capabilities, making it suitable for authorized red-team research, CTFs, vulnerability analysis, SOC automation, and security-agent applications.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":131072,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.5,"min_completion_price":3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"infron/us","service_tier":"standard","endpoint_name":"Qwen/Qwen3.8-27B-Abliterated-Cyber","prompt_price":0.5,"completion_price":3,"context_length":256000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"}]},{"id":"deepseek/deepseek-v4-pro-0813","object":"model","created":1626777600,"model_id":"deepseek/deepseek-v4-pro-0813","canonical_slug":"deepseek/deepseek-v4-pro-0813","display_name":"DeepSeek: Deepseek V4 Pro 0813","description":"1.6T total / 49B active params. Performance rivaling the world's top closed-source models.","model_family":"DeepSeek","model_family_id":9,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":384000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.5088,"min_completion_price":1.5264,"supported_endpoint_types":["openai"],"provider_count":10,"providers":[{"provider_slug":"alibaba/cn/flex","service_tier":"flex","endpoint_name":"deepseek-v4-pro-0813","prompt_price":0.5088,"completion_price":1.5264,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"deepseek-v4-pro-0813","prompt_price":0.5088,"completion_price":1.5264,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/hk","service_tier":"standard","endpoint_name":"deepseek-v4-pro-0813","prompt_price":0.5088,"completion_price":1.5264,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"deepseek-v4-pro-0813","prompt_price":0.5088,"completion_price":1.5264,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/jp","service_tier":"standard","endpoint_name":"deepseek-v4-pro-0813","prompt_price":0.5088,"completion_price":1.5264,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"deepseek-v4-pro-0813","prompt_price":0.528,"completion_price":1.584,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"tencentcloud","service_tier":"standard","endpoint_name":"deepseek-v4-pro-0813","prompt_price":1.056,"completion_price":3.168,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"deepseek","service_tier":"standard","endpoint_name":"deepseek-v4-pro","prompt_price":1.32,"completion_price":3.96,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"baidu-cloud","service_tier":"flex","endpoint_name":"deepseek-v4-pro-0813-intl","prompt_price":1.32,"completion_price":3.96,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"mangoboost","service_tier":"standard","endpoint_name":"deepseek-ai/DeepSeek-V4-Pro-0813","prompt_price":1.5,"completion_price":3,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-5.2","object":"model","created":1626777600,"model_id":"z-ai/glm-5.2","canonical_slug":"z-ai/glm-5.2","display_name":"Z.AI: GLM 5.2","description":"GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks. With a truly usable 1M-token context window, it can handle project-level engineering context, execute long-running tasks more reliably, follow engineering standards more consistently, and complete the full development workflow from requirements to multi-platform deployment in a single task.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.55,"min_completion_price":1.76,"supported_endpoint_types":["openai"],"provider_count":8,"providers":[{"provider_slug":"alibaba/cn/flex","service_tier":"flex","endpoint_name":"glm-5.2","prompt_price":0.55,"completion_price":1.9255,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"glm-5.2","prompt_price":0.55,"completion_price":1.9255,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/hk","service_tier":"standard","endpoint_name":"glm-5.2","prompt_price":0.55,"completion_price":1.9255,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"glm-5.2","prompt_price":0.55,"completion_price":1.9255,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/jp","service_tier":"standard","endpoint_name":"glm-5.2","prompt_price":0.55,"completion_price":1.9255,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"baidu-cloud","service_tier":"flex","endpoint_name":"glm-5.2","prompt_price":0.56,"completion_price":1.76,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"glm-5.2","prompt_price":0.7,"completion_price":2.2,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-5.2","prompt_price":1.4,"completion_price":4.4,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-3.5-flash","object":"model","created":1626777600,"model_id":"google/gemini-3.5-flash","canonical_slug":"google/gemini-3.5-flash","display_name":"Google: Gemini 3.5 Flash","description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs.\n\nDefaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.","model_family":"Gemini","model_family_id":15,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.5625,"min_completion_price":3.375,"supported_endpoint_types":["gemini","openai"],"provider_count":4,"providers":[{"provider_slug":"google-vertex/flex","service_tier":"flex","endpoint_name":"gemini-3.5-flash","prompt_price":0.5625,"completion_price":3.375,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3.5-flash","prompt_price":1.125,"completion_price":6.75,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-3.5-flash","prompt_price":1.5,"completion_price":9,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-vertex/priority","service_tier":"priority","endpoint_name":"gemini-3.5-flash","prompt_price":2.025,"completion_price":12.15,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"moonshotai/kimi-k2-0905","object":"model","created":1626777600,"model_id":"moonshotai/kimi-k2-0905","canonical_slug":"moonshotai/kimi-k2-0905","display_name":"MoonshotAI: Kimi K2 0905","description":"Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.","model_family":"Kimi","model_family_id":27,"model_version":"2","category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.6,"min_completion_price":2.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"novita","service_tier":"standard","endpoint_name":"moonshotai/kimi-k2-0905","prompt_price":0.6,"completion_price":2.5,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-4.5","object":"model","created":1626777600,"model_id":"z-ai/glm-4.5","canonical_slug":"z-ai/glm-4.5","display_name":"Z.AI: GLM 4.5","description":"GLM-4.5 and GLM-4.5-Air are our latest flagship models, purpose-built as foundational models for agent-oriented applications. Both leverage a Mixture-of-Experts (MoE) architecture. GLM-4.5 has a total parameter count of 355B with 32B active parameters per forward pass, while GLM-4.5-Air adopts a more streamlined design with 106B total parameters and 12B active parameters.\nBoth models share a similar training pipeline: an initial pretraining phase on 15 trillion tokens of general-domain data, followed by targeted fine-tuning on datasets covering code, reasoning, and agent-specific tasks. The context length has been extended to 128k tokens, and reinforcement learning was applied to further enhance reasoning, coding, and agent performance.\nGLM-4.5 and GLM-4.5-Air are optimized for tool invocation, web browsing, software engineering, and front-end development. They can be integrated into code-centric agents such as Claude Code and Roo Code, and also support arbitrary agent applications through tool invocation APIs.\nBoth models support hybrid reasoning modes, offering two execution modes: Thinking Mode for complex reasoning and tool usage, and Non-Thinking Mode for instant responses. These modes can be toggled via the thinking.typeparameter (with enabled and disabled settings), and dynamic thinking is enabled by default.","model_family":"GLM","model_family_id":17,"model_version":"4.5","category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":96000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.6,"min_completion_price":2.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4.5","prompt_price":0.6,"completion_price":2.2,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-4.5v","object":"model","created":1626777600,"model_id":"z-ai/glm-4.5v","canonical_slug":"z-ai/glm-4.5v","display_name":"Z.AI: GLM 4.5V","description":"GLM-4.5 and GLM-4.5-Air are our latest flagship models, purpose-built as foundational models for agent-oriented applications. Both leverage a Mixture-of-Experts (MoE) architecture. GLM-4.5 has a total parameter count of 355B with 32B active parameters per forward pass, while GLM-4.5-Air adopts a more streamlined design with 106B total parameters and 12B active parameters.\nBoth models share a similar training pipeline: an initial pretraining phase on 15 trillion tokens of general-domain data, followed by targeted fine-tuning on datasets covering code, reasoning, and agent-specific tasks. The context length has been extended to 128k tokens, and reinforcement learning was applied to further enhance reasoning, coding, and agent performance.\nGLM-4.5 and GLM-4.5-Air are optimized for tool invocation, web browsing, software engineering, and front-end development. They can be integrated into code-centric agents such as Claude Code and Roo Code, and also support arbitrary agent applications through tool invocation APIs.\nBoth models support hybrid reasoning modes, offering two execution modes: Thinking Mode for complex reasoning and tool usage, and Non-Thinking Mode for instant responses. These modes can be toggled via the thinking.typeparameter (with enabled and disabled settings), and dynamic thinking is enabled by default.","model_family":"GLM","model_family_id":17,"model_version":"4.5v","category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":96000,"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.6,"min_completion_price":1.8,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4.5v","prompt_price":0.6,"completion_price":1.8,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"moonshotai/kimi-k2-thinking","object":"model","created":1626777600,"model_id":"moonshotai/kimi-k2-thinking","canonical_slug":"moonshotai/kimi-k2-thinking","display_name":"Moonshot: Kimi K2 Thinking","description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift.\n\nIt sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.","model_family":"Kimi","model_family_id":27,"model_version":"2","category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.6,"min_completion_price":2.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"moonshotai/Kimi-K2-Thinking","prompt_price":0.6,"completion_price":2.5,"context_length":262140,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"qwen/qwen3-max","object":"model","created":1626777600,"model_id":"qwen/qwen3-max","canonical_slug":"qwen/qwen3-max","display_name":"Qwen: Qwen3 Max","description":"Qwen/qwen3-max, Enhanced with specialized upgrades in agent programming and tool calling. This official release achieves domain SOTA performance, supporting more complex agent scenarios.\n","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":65536,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.6,"min_completion_price":3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3-max","prompt_price":0.6,"completion_price":3,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemma-4-26b-a4b-it-cybersecurity","object":"model","created":1626777600,"model_id":"google/gemma-4-26b-a4b-it-cybersecurity","canonical_slug":"google/gemma-4-26b-a4b-it-cybersecurity","display_name":"Google: Gemma 4 26B A4B Cybersecurity","description":"Gemma 4 26B A4B Cybersecurity is a fine-tuned variant in the Gemma 4 26B A4B family for cybersecurity work. Applicable tasks include authorized security analysis, code review and reasoning over technical evidence.\n\n    It accepts text and images and produces text. Reasoning supports working through complex questions and multi-step tasks. Tool calling can connect the conversation to external functions executed by an application.","model_family":"Gemma","model_family_id":16,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.6,"min_completion_price":1.9,"provider_count":1,"providers":[{"provider_slug":"aoru","service_tier":"standard","endpoint_name":"google/gemma-4-26b-a4b-it-cybersecurity","prompt_price":0.6,"completion_price":1.9,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"mistral/mistral-large-4","object":"model","created":1626777600,"model_id":"mistral/mistral-large-4","canonical_slug":"mistral/mistral-large-4","display_name":"Mistral: Mistral Large 4","description":"Mistral Large 4 is a general-purpose multimodal model released by Mistral AI in public preview on October 6, 2026. Its granular mixture-of-experts architecture has a reported 1.05T total parameters, 52B active parameters and a 1.6B vision encoder. It targets multimodal understanding, document question answering and tool-assisted workflows. The official model page advertises a 1M context window, while this account catalog reports 524288 tokens; this configuration follows the live catalog limit.","model_family":"Mistral","model_family_id":37,"category_type":"LLM","context_length":524288,"max_input_tokens":524288,"max_output_tokens":262144,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.68,"min_completion_price":2.09,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mistral","service_tier":"standard","endpoint_name":"mistral-large-4","prompt_price":0.68,"completion_price":2.09,"context_length":524288,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-r1-distill-llama-70b","object":"model","created":1626777600,"model_id":"deepseek/deepseek-r1-distill-llama-70b","canonical_slug":"deepseek/deepseek-r1-distill-llama-70b","display_name":"Deepseek: Deepseek R1 Distill Llama 70B","description":"DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from DeepSeek R1. The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including:\n\nAIME 2024 pass@1: 70.0\nMATH-500 pass@1: 94.5\nCodeForces Rating: 1633\nThe model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.","model_family":"DeepSeek","model_family_id":9,"model_version":"r1","category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":16400,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.7,"min_completion_price":0.8,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"deepseek-ai/DeepSeek-R1-Distill-Llama-70B","prompt_price":0.7,"completion_price":0.8,"context_length":131000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"moonshotai/kimi-k2-instruct","object":"model","created":1626777600,"model_id":"moonshotai/kimi-k2-instruct","canonical_slug":"moonshotai/kimi-k2-instruct","display_name":"Moonshot: Kimi-K2-Instruct","description":"State-of-the-art mixture-of-experts agentic intelligence model with 1 T parameters, 128K context, and native tool use","model_family":"Kimi","model_family_id":27,"category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":65540,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.7,"min_completion_price":2.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"moonshotai/Kimi-K2-Instruct","prompt_price":0.7,"completion_price":2.5,"context_length":131070,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"aion-labs/aion-3.0-mini","object":"model","created":1626777600,"model_id":"aion-labs/aion-3.0-mini","canonical_slug":"aion-labs/aion-3.0-mini","display_name":"AionLabs: Aion 3.0 Mini","description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.","model_family":"AionLabs","model_family_id":1,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.7,"min_completion_price":1.4,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"aion-labs","service_tier":"standard","endpoint_name":"aion-labs/aion-3.0-mini","prompt_price":0.7,"completion_price":1.4,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"aion-labs/aion-3.5-mini","object":"model","created":1626777600,"model_id":"aion-labs/aion-3.5-mini","canonical_slug":"aion-labs/aion-3.5-mini","display_name":"AionLabs: Aion 3.5 Mini","description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses the same collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.","model_family":"AionLabs","model_family_id":1,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.7,"min_completion_price":1.4,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"aion-labs","service_tier":"standard","endpoint_name":"aion-labs/aion-3.5-mini","prompt_price":0.7,"completion_price":1.4,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.8-27b-uncensored","object":"model","created":1626777600,"model_id":"qwen/qwen3.8-27b-uncensored","canonical_slug":"qwen/qwen3.8-27b-uncensored","display_name":"Qwen: Qwen3.8 27B-Uncensored","description":"Qwen3.8 27B-Uncensored is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":204000,"max_input_tokens":204000,"max_output_tokens":204000,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.7,"min_completion_price":4.8,"supported_endpoint_types":["openai"],"provider_count":3,"providers":[{"provider_slug":"hai","service_tier":"priority","endpoint_name":"qwen3.8-27b-uncensored","prompt_price":0.7,"completion_price":4.8,"context_length":245760,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"unlid","service_tier":"standard","endpoint_name":"qwen3.8-27b-uncensored","prompt_price":1.5,"completion_price":9,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"infron/us","service_tier":"standard","endpoint_name":"Qwen/Qwen3.8-27B-Uncensored","prompt_price":2.5,"completion_price":15,"context_length":204000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"kwaipilot/kat-coder-pro-v2.5","object":"model","created":1626777600,"model_id":"kwaipilot/kat-coder-pro-v2.5","canonical_slug":"kwaipilot/kat-coder-pro-v2.5","display_name":"Kwaipilot: Kat Coder Pro V2.5","description":"High-end coding agent built for complex software engineering, repository-scale tasks, and autonomous development workflows.","model_family":"Kwaipilot","model_family_id":73,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262144,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.74,"min_completion_price":2.96,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"kwaipilot/kat-coder-pro-v2.5","prompt_price":0.74,"completion_price":2.96,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"meituan/longcat-2.0","object":"model","created":1626777600,"model_id":"meituan/longcat-2.0","canonical_slug":"meituan/longcat-2.0","display_name":"Meituan: LongCat-2.0","description":"LongCat-2.0 is a high-performance foundation model designed for agentic workloads. Natively supports tool use, and long-context tasks, with strong performance in code generation, automated workflows, and complex instruction execution. Compatible with Claude Code, OpenClaw, and other mainstream productivity tools.","model_family":"LongCat","model_family_id":32,"category_type":"LLM","context_length":1049000,"max_input_tokens":1049000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.75,"min_completion_price":2.95,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"siliconflow","service_tier":"standard","endpoint_name":"meituan-longcat/LongCat-2.0","prompt_price":0.75,"completion_price":2.95,"context_length":1049000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"deepseek/deepseek-v4-flash-vision-exp-cybersecurity","object":"model","created":1626777600,"model_id":"deepseek/deepseek-v4-flash-vision-exp-cybersecurity","canonical_slug":"deepseek/deepseek-v4-flash-vision-exp-cybersecurity","display_name":"DeepSeek: DeepSeek V4 Flash Vision Exp Cybersecurity","description":"DeepSeek V4 Flash Vision Experimental Cybersecurity is a security-oriented language-model variant with visual input support. It is suited to authorized cybersecurity analysis, code review and reasoning over technical material, including evidence supplied as images.\n\n    It accepts text and images and produces text. Reasoning supports working through complex questions and multi-step tasks. Tool calling can connect the conversation to external functions executed by an application.","model_family":"DeepSeek","model_family_id":9,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.75,"min_completion_price":2.5,"provider_count":1,"providers":[{"provider_slug":"aoru","service_tier":"standard","endpoint_name":"deepseek/deepseek-v4-flash-vision-exp-cybersecurity","prompt_price":0.75,"completion_price":2.5,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"}]},{"id":"z-ai/glm-5.3-flash-cybersecurity","object":"model","created":1626777600,"model_id":"z-ai/glm-5.3-flash-cybersecurity","canonical_slug":"z-ai/glm-5.3-flash-cybersecurity","display_name":"Z.AI: GLM 5.3 Flash Cybersecurity","description":"GLM 5.3 Flash Cybersecurity is a fine-tuned variant in the GLM 5.3 Flash family for cybersecurity work. Applicable tasks include authorized security analysis, code review and reasoning over technical evidence.\n\n    It accepts text and images and produces text. Reasoning supports working through complex questions and multi-step tasks. Tool calling can connect the conversation to external functions executed by an application.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.75,"min_completion_price":12.5,"provider_count":1,"providers":[{"provider_slug":"aoru","service_tier":"standard","endpoint_name":"z-ai/glm-5.3-flash-cybersecurity","prompt_price":0.75,"completion_price":12.5,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"}]},{"id":"qwen/qwen3-coder","object":"model","created":1626777600,"model_id":"qwen/qwen3-coder","canonical_slug":"qwen/qwen3-coder","display_name":"Qwen: Qwen3 Coder","description":"Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262140,"max_input_tokens":262140,"max_output_tokens":65540,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.78,"min_completion_price":3.8,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"atlas-cloud","service_tier":"standard","endpoint_name":"Qwen/Qwen3-Coder","prompt_price":0.78,"completion_price":3.8,"context_length":262140,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"aion-labs/aion-2.0","object":"model","created":1626777600,"model_id":"aion-labs/aion-2.0","canonical_slug":"aion-labs/aion-2.0","display_name":"AionLabs: Aion 2.0","description":"A variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging. It also handles mature and darker themes with more nuance and depth. ","model_family":"AionLabs","model_family_id":1,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.8,"min_completion_price":1.6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"aion-labs","service_tier":"standard","endpoint_name":"aion-labs/aion-2.0","prompt_price":0.8,"completion_price":1.6,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"morph/morph-v3-fast","object":"model","created":1626777600,"model_id":"morph/morph-v3-fast","canonical_slug":"morph/morph-v3-fast","display_name":"Morph: Morph V3 Fast","description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations.\n\nThe model requires the prompt to be in the following format:\n\u003cinstruction\u003e{instruction}\u003c/instruction\u003e\n\u003ccode\u003e{initial_code}\u003c/code\u003e\n\u003cupdate\u003e{edit_snippet}\u003c/update\u003e","model_family":"morph","model_family_id":86,"category_type":"LLM","context_length":81900,"max_input_tokens":81900,"max_output_tokens":38000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.8,"min_completion_price":1.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"morph","service_tier":"standard","endpoint_name":"morph-v3-fast","prompt_price":0.8,"completion_price":1.2,"context_length":81900,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"x-ai/grok-build-0.1","object":"model","created":1626777600,"model_id":"x-ai/grok-build-0.1","canonical_slug":"x-ai/grok-build-0.1","display_name":"xAI: Grok Build 0.1","description":"Grok Build 0.1 is xAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding agents, tool use, and multi-step development tasks. The model powers xAI’s Grok Build CLI and features a 256K context window with no text output limit, making it well suited for long-horizon coding and automation workflows. Currently in early access.","model_family":"Grok","model_family_id":20,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":256000,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.8,"min_completion_price":1.6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-build-0.1","prompt_price":0.8,"completion_price":1.6,"context_length":256000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"amazon/nova-pro-v1","object":"model","created":1626777600,"model_id":"amazon/nova-pro-v1","canonical_slug":"amazon/nova-pro-v1","display_name":"Amazon: Nova Pro 1.0","description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. It achieves state-of-the-art performance on key benchmarks including visual question answering (TextVQA) and video understanding (VATEX).\n\nAmazon Nova Pro demonstrates strong capabilities in processing both visual and textual information and at analyzing financial documents.","model_family":"Nova","model_family_id":76,"category_type":"LLM","context_length":300000,"max_input_tokens":300000,"max_output_tokens":5100,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.8,"min_completion_price":3.2,"supported_endpoint_types":["anthropic","openai"],"provider_count":1,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"us.amazon.nova-pro-v1","prompt_price":0.8,"completion_price":3.2,"context_length":300000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.5-9b-abliterated","object":"model","created":1626777600,"model_id":"qwen/qwen3.5-9b-abliterated","canonical_slug":"qwen/qwen3.5-9b-abliterated","display_name":"Qwen3.5 9B Abliterated","description":"huihui-ai's abliteration of Qwen3.5 9B: a small model with refusals removed from the weights and reasoning, vision and tool calling kept. Thinking is off unless you turn it on.\n\n    Huihui-ai's card identifies a modified Qwen3.5-9B checkpoint created through abliteration and labels it image-to-text. This is a small modified vision-language model for language, coding and reasoning workloads. Unlid documents thinking as disabled by default and permits enabling it.\n\n    Unlid declares a 32,768-token context and up to 32,768 output tokens. Input: text, image; output: text. Tool calling is supported. Reasoning is supported; it can be disabled. Reasoning tokens, when generated, count toward the output budget and are charged as output. Prices are USD per million tokens from the live catalog; missing cache discounts use the normal input price under Unlid billing rules. Limits and capabilities are provider declarations, not results of an inference test.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.816,"min_completion_price":1.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"unlid","service_tier":"standard","endpoint_name":"qwen3.5-9b-abliterated","prompt_price":0.816,"completion_price":1.2,"context_length":32768,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.7-max","object":"model","created":1626777600,"model_id":"qwen/qwen3.7-max","canonical_slug":"qwen/qwen3.7-max","display_name":"Qwen: Qwen3.7 Max","description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks, and long-horizon autonomous execution. The model offers notable gains in coding and agentic performance over prior Qwen generations and supports explicit prompt caching for efficient repeated context use.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":64000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.825,"min_completion_price":2.4755,"supported_endpoint_types":["openai"],"provider_count":3,"providers":[{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"qwen3.7-max","prompt_price":0.825,"completion_price":2.4755,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"qwen3.7-max","prompt_price":0.825,"completion_price":2.4755,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.7-max","prompt_price":1.25,"completion_price":3.75,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.8-max","object":"model","created":1626777600,"model_id":"qwen/qwen3.8-max","canonical_slug":"qwen/qwen3.8-max","display_name":"Qwen: Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship delivering a comprehensive leap in coding and professional work. Autonomously codes and delivers complete projects spanning 10+ days. Handles hundreds of specialized tasks across legal, financial, design, and other professional domains, producing production-grade results end-to-end in a single conversation. Native visual understanding runs through the full cycle of planning, execution, and verification, enabling deep semantic analysis of ultra-long documents and extended video content. In long-horizon tasks, plans autonomously, iterates through closed feedback loops, and continuously evolves.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.825,"min_completion_price":2.4755,"supported_endpoint_types":["openai"],"provider_count":6,"providers":[{"provider_slug":"alibaba/cn","service_tier":"flex","endpoint_name":"qwen3.8-max","prompt_price":0.825,"completion_price":2.4755,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/us","service_tier":"standard","endpoint_name":"qwen3.8-max","prompt_price":0.825,"completion_price":2.4755,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/hk","service_tier":"standard","endpoint_name":"qwen3.8-max","prompt_price":0.825,"completion_price":2.4755,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"qwen3.8-max","prompt_price":0.825,"completion_price":2.4755,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/jp","service_tier":"standard","endpoint_name":"qwen3.8-max","prompt_price":0.825,"completion_price":2.4755,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.8-max","prompt_price":1,"completion_price":3,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"tencent/hy4-preview","object":"model","created":1626777600,"model_id":"tencent/hy4-preview","canonical_slug":"tencent/hy4-preview","display_name":"Tencent: Hy4 Preview","description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that require planning, context continuity, and sustained multi-step execution.","model_family":"Hunyuan","model_family_id":24,"category_type":"LLM","context_length":1024000,"max_input_tokens":1024000,"max_output_tokens":64000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.834,"min_completion_price":2.501,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"tencentcloud","service_tier":"standard","endpoint_name":"hy4-preview","prompt_price":0.834,"completion_price":2.501,"context_length":1024000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"sao10k/l3.1-70b-euryale-v2.2","object":"model","created":1626777600,"model_id":"sao10k/l3.1-70b-euryale-v2.2","canonical_slug":"sao10k/l3.1-70b-euryale-v2.2","display_name":"Sao10K: Llama 3.1 Euryale 70B v2.2","description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.1.","model_family":"Sao10k","model_family_id":78,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":16400,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.85,"min_completion_price":0.85,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Sao10K/L3.1-70B-Euryale-v2.2","prompt_price":0.85,"completion_price":0.85,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"sao10k/l3.3-70b-euryale-v2.3","object":"model","created":1626777600,"model_id":"sao10k/l3.3-70b-euryale-v2.3","canonical_slug":"sao10k/l3.3-70b-euryale-v2.3","display_name":"Sao10K: Llama 3.3 Euryale 70B v2.3","description":"Euryale L3.3 70B is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.2.","model_family":"Sao10k","model_family_id":78,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":16400,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.85,"min_completion_price":0.85,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Sao10K/L3.3-70B-Euryale-v2.3","prompt_price":0.85,"completion_price":0.85,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"infermatic","service_tier":"standard","endpoint_name":"Sao10K-L3.3-70B-Euryale-v2.3-FP8-Dynamic","prompt_price":0.85,"completion_price":0.85,"context_length":32000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"morph/morph-v3-large","object":"model","created":1626777600,"model_id":"morph/morph-v3-large","canonical_slug":"morph/morph-v3-large","display_name":"Morph: Morph V3 Large","description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations.\n\nThe model requires the prompt to be in the following format:\n\u003cinstruction\u003e{instruction}\u003c/instruction\u003e\n\u003ccode\u003e{initial_code}\u003c/code\u003e\n\u003cupdate\u003e{edit_snippet}\u003c/update\u003e","model_family":"morph","model_family_id":86,"category_type":"LLM","context_length":262100,"max_input_tokens":262100,"max_output_tokens":131100,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9,"min_completion_price":1.9,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"morph","service_tier":"standard","endpoint_name":"morph-v3-large","prompt_price":0.9,"completion_price":1.9,"context_length":262100,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/o1-mini","object":"model","created":1626777600,"model_id":"openai/o1-mini","canonical_slug":"openai/o1-mini","display_name":"OpenAI: O1 Mini","description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding.\n\nThe o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. ","model_family":"OpenAI GPT","model_family_id":44,"model_version":"o1","category_type":"LLM","context_length":200000,"max_input_tokens":200000,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9075,"min_completion_price":3.63,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"o1-mini","prompt_price":0.9075,"completion_price":3.63,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/o3-mini","object":"model","created":1626777600,"model_id":"openai/o3-mini","canonical_slug":"openai/o3-mini","display_name":"OpenAI: O3 Mini","description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding.\n\nThis model supports the reasoning_effort parameter, which can be set to \"high\", \"medium\", or \"low\" to control the thinking time of the model. The default is \"medium\". OpenRouter also offers the model slug openai/o3-mini-high to default the parameter to \"high\".\n\nThe model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities.\n\nThe model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"o3","category_type":"LLM","context_length":200000,"max_input_tokens":200000,"max_output_tokens":1,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9075,"min_completion_price":3.63,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"o3-mini","prompt_price":0.9075,"completion_price":3.63,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/o4-mini","object":"model","created":1626777600,"model_id":"openai/o4-mini","canonical_slug":"openai/o4-mini","display_name":"OpenAI: O4 Mini","description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains.\n\nDespite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.","model_family":"OpenAI GPT","model_family_id":44,"model_version":"o4","category_type":"LLM","context_length":200000,"max_input_tokens":200000,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9075,"min_completion_price":3.63,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"o4-mini","prompt_price":0.9075,"completion_price":3.63,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5-chat","object":"model","created":1626777600,"model_id":"openai/gpt-5-chat","canonical_slug":"openai/gpt-5-chat","display_name":"OpenAI: GPT 5 chat","description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like \"think hard about this.\" Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":128000,"max_input_tokens":16400,"max_output_tokens":16400,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9375,"min_completion_price":7.5,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5-chat","prompt_price":0.9375,"completion_price":7.5,"context_length":400,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5-chat-latest","prompt_price":1.25,"completion_price":10,"context_length":400,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-2.5-pro","object":"model","created":1626777600,"model_id":"google/gemini-2.5-pro","canonical_slug":"google/gemini-2.5-pro","display_name":"Google: Gemini 2.5 pro","description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.","model_family":"Gemini","model_family_id":15,"model_version":"2.5","category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"input_modalities":["Text","Code","Image","Audio","Video","PDF"],"output_modalities":["Text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9375,"min_completion_price":7.5,"supported_endpoint_types":["gemini","openai"],"provider_count":1,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-2.5-pro","prompt_price":0.9375,"completion_price":7.5,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-2.5-pro-preview-06-05","object":"model","created":1626777600,"model_id":"google/gemini-2.5-pro-preview-06-05","canonical_slug":"google/gemini-2.5-pro-preview-06-05","display_name":"Google: Gemini 2.5 pro preview 06 05","description":"Gemini 2.5 Pro is our most advanced reasoning Gemini model, capable of solving complex problems. Gemini 2.5 Pro can comprehend vast datasets and challenging problems from different information sources, including text, audio, images, video, and even entire code repositories.","model_family":"Gemini","model_family_id":15,"model_version":"2.5","category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"input_modalities":["Text","Code","Image","Audio","Video","PDF"],"output_modalities":["Text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9375,"min_completion_price":7.5,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-2.5-pro","prompt_price":0.9375,"completion_price":7.5,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-2.5-pro","prompt_price":1.25,"completion_price":10,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-2.5-pro-preview-05-06","object":"model","created":1626777600,"model_id":"google/gemini-2.5-pro-preview-05-06","canonical_slug":"google/gemini-2.5-pro-preview-05-06","display_name":"Google: Gemini 2.5 pro preview 05 06","description":"Gemini 2.5 Pro is our most advanced reasoning Gemini model, capable of solving complex problems. Gemini 2.5 Pro can comprehend vast datasets and challenging problems from different information sources, including text, audio, images, video, and even entire code repositories.","model_family":"Gemini","model_family_id":15,"model_version":"2.5","category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"input_modalities":["Text","Code","Image","Audio","Video","PDF"],"output_modalities":["Text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9375,"min_completion_price":7.5,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-2.5-pro","prompt_price":0.9375,"completion_price":7.5,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-2.5-pro","prompt_price":1.25,"completion_price":10,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-2.5-pro-preview-03-25","object":"model","created":1626777600,"model_id":"google/gemini-2.5-pro-preview-03-25","canonical_slug":"google/gemini-2.5-pro-preview-03-25","display_name":"Google: Gemini 2.5 pro preview 03 25","description":"Gemini 2.5 Pro is our most advanced reasoning Gemini model, capable of solving complex problems. Gemini 2.5 Pro can comprehend vast datasets and challenging problems from different information sources, including text, audio, images, video, and even entire code repositories.","model_family":"Gemini","model_family_id":15,"model_version":"2.5","category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"input_modalities":["Text","Code","Image","Audio","Video","PDF"],"output_modalities":["Text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":0.9375,"min_completion_price":7.5,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-2.5-pro","prompt_price":0.9375,"completion_price":7.5,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-2.5-pro","prompt_price":1.25,"completion_price":10,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"nousresearch/hermes-3-llama-3.1-405b","object":"model","created":1626777600,"model_id":"nousresearch/hermes-3-llama-3.1-405b","canonical_slug":"nousresearch/hermes-3-llama-3.1-405b","display_name":"Nous: Hermes 3 Llama 3.1 405B","description":"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.\n\nHermes 3 405B is a frontier-level, full-parameter finetune of the Llama-3.1 405B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.\n\nThe Hermes 3 series builds and expands on the Hermes 2 set of capabilities, including more powerful and reliable function calling and structured output capabilities, generalist assistant capabilities, and improved code generation skills.\n\nHermes 3 is competitive, if not superior, to Llama-3.1 Instruct models at general capabilities, with varying strengths and weaknesses attributable between the two.","model_family":"Nous","model_family_id":42,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":1,"min_completion_price":1,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"NousResearch/Hermes-3-Llama-3.1-405B","prompt_price":1,"completion_price":1,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"anthropic/claude-haiku-4.5","object":"model","created":1626777600,"model_id":"anthropic/claude-haiku-4.5","canonical_slug":"anthropic/claude-haiku-4.5","display_name":"Anthropic: Claude Haiku 4.5","description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications.\n\nIt introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring \u003e73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":200000,"max_input_tokens":200000,"max_output_tokens":64000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":1,"min_completion_price":5,"supported_endpoint_types":["anthropic","openai"],"provider_count":2,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-haiku-4-5-20251001-v1:0","prompt_price":1,"completion_price":5,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-haiku-4-5-20251001","prompt_price":1,"completion_price":5,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"moonshotai/kimi-v1-32k","object":"model","created":1626777600,"model_id":"moonshotai/kimi-v1-32k","canonical_slug":"moonshotai/kimi-v1-32k","display_name":"Moonshot: Kimi V1 32K","description":"Kimi v1 32k is a large‑language model in Moonshot AI’s moonshot‑v1 series that offers a 32 k token context window, enabling it to ingest and generate up to roughly 20 k Chinese characters (or an equivalent amount of English text) in a single turn, which is ideal for processing long documents, multi‑turn dialogues, and complex summarisation tasks; built on a Transformer architecture with around 2 trillion parameters and trained primarily on 4‑5 TB of Chinese‑language data (supplemented by multilingual corpora), it delivers performance comparable to leading global models while delivering superior handling of Chinese semantics and nuanced language nuances; the model supports advanced developer‑oriented features such as ToolCalls (function calling), JSON Mode for structured output, Partial Mode for streaming responses, and integrated web‑search capabilities, and it benefits from the platform’s automatic context‑caching system that reduces token‑costs for repeated content; although it does not yet provide multimodal (image or audio) input, it is optimized for low hallucination, higher factuality, and faster inference on Nvidia‑GPU clusters via ByteDance’s Volcano Engine cloud, making it a technically advanced, cost‑effective solution for enterprises and developers seeking high‑quality, long‑context generation in both Chinese and English.","model_family":"Kimi","model_family_id":27,"model_version":"1","category_type":"LLM","context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":1,"min_completion_price":3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"moonshotai","service_tier":"standard","endpoint_name":"moonshot-v1-32k","prompt_price":1,"completion_price":3,"context_length":32768,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.6-terra","object":"model","created":1626777600,"model_id":"openai/gpt-5.6-terra","canonical_slug":"openai/gpt-5.6-terra","display_name":"OpenAI: GPT-5.6 Terra","description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.\n","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1,"min_completion_price":6,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"openai/flex","service_tier":"flex","endpoint_name":"gpt-5.6-terra","prompt_price":1,"completion_price":6,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5.6-terra","prompt_price":1.5,"completion_price":9,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.6-terra","prompt_price":2,"completion_price":12,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai/priority","service_tier":"priority","endpoint_name":"gpt-5.6-terra","prompt_price":4,"completion_price":24,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"thinkingmachines/inkling","object":"model","created":1626777600,"model_id":"thinkingmachines/inkling","canonical_slug":"thinkingmachines/inkling","display_name":"Thinking Machines: Inkling","description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.","model_family":"Thinkingmachines","model_family_id":116,"category_type":"LLM","context_length":524288,"max_input_tokens":524288,"max_output_tokens":524288,"input_modalities":["text","image","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1,"min_completion_price":4.05,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"together","service_tier":"standard","endpoint_name":"thinkingmachines/inkling","prompt_price":1,"completion_price":4.05,"context_length":524288,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.8-2.4t-a95b","object":"model","created":1626777600,"model_id":"qwen/qwen3.8-2.4t-a95b","canonical_slug":"qwen/qwen3.8-2.4t-a95b","display_name":"Qwen: Qwen3.8 2.4T A95B","description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":131100,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1,"min_completion_price":3,"supported_endpoint_types":["openai"],"provider_count":3,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.8-2.4t-a95b","prompt_price":1,"completion_price":3,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"Qwen/Qwen3.8-2.4T-A95B","prompt_price":1.8,"completion_price":5.4,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"fireworks","service_tier":"standard","endpoint_name":"accounts/fireworks/models/qwen3p8-2p4t-a95b","prompt_price":2,"completion_price":6,"context_length":262144,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"abliteration-ai/abliterated-model","object":"model","created":1626777600,"model_id":"abliteration-ai/abliterated-model","canonical_slug":"abliteration-ai/abliterated-model","display_name":"Abliterated Model","description":"Abliterated Model served by Abliteration.","model_family":"Abliteration","model_family_id":123,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":262134,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1,"min_completion_price":3,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"abliteration","service_tier":"standard","endpoint_name":"abliterated-model","prompt_price":1,"completion_price":3,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp16"}]},{"id":"z-ai/glm-5.3-flash-uncensored","object":"model","created":1626777600,"model_id":"z-ai/glm-5.3-flash-uncensored","canonical_slug":"z-ai/glm-5.3-flash-uncensored","display_name":"Z.AI: GLM 5.3 Flash Uncensored","description":"GLM 5.3 Flash Uncensored is an uncensored fine-tune of the efficient 320B mixture-of-experts reasoning model with provider-dependent vision support, built for unrestricted chat, creative writing, coding, agentic work, tool use, and long-context tasks.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":32800,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1,"min_completion_price":4,"supported_endpoint_types":["openai"],"provider_count":3,"providers":[{"provider_slug":"arnict","service_tier":"standard","endpoint_name":"zai/glm-5.3-flash-uncensored","prompt_price":1,"completion_price":4,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"},{"provider_slug":"unlid","service_tier":"standard","endpoint_name":"glm-5.3-flash-uncensored","prompt_price":1.2,"completion_price":4.8,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"hai","service_tier":"priority","endpoint_name":"glm-5.3-flash-uncensored","prompt_price":4,"completion_price":8,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"openai/gpt-6.1-sol","object":"model","created":1626777600,"model_id":"openai/gpt-6.1-sol","canonical_slug":"openai/gpt-6.1-sol","display_name":"OpenAI: GPT-6.1 Sol","description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1,"min_completion_price":5,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"openai/flex","service_tier":"flex","endpoint_name":"gpt-6.1-sol","prompt_price":1,"completion_price":5,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-6.1-sol","prompt_price":1.5,"completion_price":7.5,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-6.1-sol","prompt_price":2,"completion_price":10,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai/priority","service_tier":"priority","endpoint_name":"gpt-6.1-sol","prompt_price":4,"completion_price":20,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"stepfun/step-5-preview","object":"model","created":1626777600,"model_id":"stepfun/step-5-preview","canonical_slug":"stepfun/step-5-preview","display_name":"StepFun: Step 5 Preview","description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional knowledge work, with particular strength in finance.\n\nIt is designed for extended tasks that span large codebases and documents, using tools and refining results over multiple steps.","model_family":"Step","model_family_id":81,"category_type":"LLM","context_length":1024000,"max_input_tokens":1024000,"max_output_tokens":64000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1,"min_completion_price":2.7,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"stepfun","service_tier":"standard","endpoint_name":"step-5-preview","prompt_price":1,"completion_price":2.7,"context_length":1024000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-4.5-airx","object":"model","created":1626777600,"model_id":"z-ai/glm-4.5-airx","canonical_slug":"z-ai/glm-4.5-airx","display_name":"Z.AI: GLM 4.5 AirX","description":"Enhanced GLM-4.5 Air variant.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":32000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":1.1,"min_completion_price":4.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4.5-airx","prompt_price":1.1,"completion_price":4.5,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/gemini-nano-banana-2.1/text-to-image","object":"model","created":1626777600,"model_id":"google/gemini-nano-banana-2.1/text-to-image","canonical_slug":"google/gemini-nano-banana-2.1/text-to-image","display_name":"Google: Gemini Nano Banana 2.1 (Text to Image)","description":"Nano Banana 2.1 by Google generates images from text prompts, with output resolutions up to 4K, adjustable aspect ratios, and optional web search grounding.","model_family":"Gemini","model_family_id":15,"category_type":"Text to Image","context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["image"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.125,"min_completion_price":22.5,"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-nano-banana-2.1","prompt_price":1.125,"completion_price":22.5,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-nano-banana-2.1","prompt_price":1.5,"completion_price":30,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"google/gemini-nano-banana-2.1/image-to-image","object":"model","created":1626777600,"model_id":"google/gemini-nano-banana-2.1/image-to-image","canonical_slug":"google/gemini-nano-banana-2.1/image-to-image","display_name":"Google: Gemini Nano Banana 2.1 (Image to Image)","description":"Nano Banana 2.1 Edit by Google transforms reference images using text instructions, with output resolutions up to 4K and optional video or PDF context.","model_family":"Gemini","model_family_id":15,"category_type":"Image to Image","context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.125,"min_completion_price":22.5,"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-nano-banana-2.1","prompt_price":1.125,"completion_price":22.5,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-nano-banana-2.1","prompt_price":1.5,"completion_price":30,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"nvidia/llama-3.1-nemotron-70b-instruct","object":"model","created":1626777600,"model_id":"nvidia/llama-3.1-nemotron-70b-instruct","canonical_slug":"nvidia/llama-3.1-nemotron-70b-instruct","display_name":"NVIDIA: Llama 3.1 Nemotron 70B Instruct","description":"NVIDIA's Llama 3.1 Nemotron 70B is a language model designed for generating precise and useful responses. Leveraging Llama 3.1 70B architecture and Reinforcement Learning from Human Feedback (RLHF), it excels in automatic alignment benchmarks. This model is tailored for applications requiring high accuracy in helpfulness and response generation, suitable for diverse user queries across multiple domains.","model_family":"Nemotron","model_family_id":41,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":16400,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":1.2,"min_completion_price":1.2,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"deepinfra","service_tier":"standard","endpoint_name":"nvidia/Llama-3.1-Nemotron-70B-Instruct","prompt_price":1.2,"completion_price":1.2,"context_length":131072,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"qwen/qwen3.8-27b-abliterated","object":"model","created":1626777600,"model_id":"qwen/qwen3.8-27b-abliterated","canonical_slug":"qwen/qwen3.8-27b-abliterated","display_name":"Qwen3.8 27B Abliterated","description":"huihui-ai's abliteration of Qwen3.8 27B: the refusal direction is removed from the weights, reasoning, coding, vision and tool calling are kept. Thinking is on unless you switch it off.\n\n    Huihui-ai's checkpoint card describes targeted abliteration of Qwen3.8-27B, with layers 18 through 51 modified in its current revision and visual and multi-token prediction components left unchanged. It is a distinct modified checkpoint, rather than the unchanged Qwen base or an unspecified Uncensored route.\n\n    Unlid declares a 32,768-token context and up to 32,768 output tokens. Input: text, image; output: text. Tool calling is supported. Reasoning is supported; it can be disabled. Reasoning tokens, when generated, count toward the output budget and are charged as output. Prices are USD per million tokens from the live catalog; missing cache discounts use the normal input price under Unlid billing rules. Limits and capabilities are provider declarations, not results of an inference test.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":32768,"max_input_tokens":32768,"max_output_tokens":32768,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.2,"min_completion_price":9,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"unlid","service_tier":"standard","endpoint_name":"qwen3.8-27b-abliterated","prompt_price":1.2,"completion_price":9,"context_length":32768,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"meta-ai/muse-spark-1.1","object":"model","created":1626777600,"model_id":"meta-ai/muse-spark-1.1","canonical_slug":"meta-ai/muse-spark-1.1","display_name":"Meta AI: Muse Spark 1.1","description":"Muse Spark offers competitive performance in multimodal perception, reasoning, health, and agentic tasks.","model_family":"Muse","model_family_id":113,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":1048576,"input_modalities":["text","image","video","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.25,"min_completion_price":4.25,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"meta-ai","service_tier":"standard","endpoint_name":"muse-spark-1.1","prompt_price":1.25,"completion_price":4.25,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-5.3-flash-abliterated","object":"model","created":1626777600,"model_id":"z-ai/glm-5.3-flash-abliterated","canonical_slug":"z-ai/glm-5.3-flash-abliterated","display_name":"Z.AI: GLM 5.3 Flash Abliterated","description":"GLM 5.3 Flash Abliterated is a derivative of the GLM-5.3-Flash open-weight language model, with weight-level modifications intended to reduce refusal behavior. It supports text conversation, reasoning and tool calling for coding, cybersecurity research and agent workflows. Long-context text processing supports working with extensive code, technical documentation and multi-step task histories.\n\n    Applicable scenarios include code analysis, authorized security testing, AI red-team evaluation and agent behavior testing. Tool calling allows a surrounding application to execute functions and return results for subsequent reasoning. The Flash variant emphasizes cost-efficient use in iterative coding and security workflows.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.25,"min_completion_price":4,"provider_count":1,"providers":[{"provider_slug":"refuseless","service_tier":"standard","endpoint_name":"glm-5.3-flash-abliterated","prompt_price":1.25,"completion_price":4,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.8-27b-cybersecurity","object":"model","created":1626777600,"model_id":"qwen/qwen3.8-27b-cybersecurity","canonical_slug":"qwen/qwen3.8-27b-cybersecurity","display_name":"Qwen: Qwen3.8 27B Cybersecurity","description":"Qwen 3.8 27B Cybersecurity is a fine-tuned variant in the Qwen3.8 27B family for cybersecurity work. Applicable tasks include authorized security analysis, code review and reasoning over technical evidence.\n\n    It accepts text and images and produces text. Reasoning supports working through complex questions and multi-step tasks. Tool calling can connect the conversation to external functions executed by an application.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.25,"min_completion_price":37.5,"provider_count":1,"providers":[{"provider_slug":"aoru","service_tier":"standard","endpoint_name":"qwen/qwen3.8-27b-cybersecurity","prompt_price":1.25,"completion_price":37.5,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp4"}]},{"id":"z-ai/glm-5.2-fast","object":"model","created":1626777600,"model_id":"z-ai/glm-5.2-fast","canonical_slug":"z-ai/glm-5.2-fast","display_name":"Z.AI: GLM 5.2 Fast","description":"GLM-5.2-Fast-Preview is the high-speed version of Zhipu AI’s flagship model, GLM-5.2. It supports an ultra-long context window of 1 million tokens and matches the capabilities of the standard GLM-5.2 edition, excelling in logical reasoning, long-text comprehension, and code generation. Through inference acceleration optimizations, its output throughput (TPS) reaches 1.5 to 2 times that of the standard version, significantly boosting output speed. It is ideally suited for scenarios where speed is critical, such as real-time conversations, multi-turn agent interactions, and streaming code generation.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.4,"min_completion_price":4.4,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"glm-5.2-fast-preview","prompt_price":1.4,"completion_price":4.4,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-5.3-prime","object":"model","created":1626777600,"model_id":"z-ai/glm-5.3-prime","canonical_slug":"z-ai/glm-5.3-prime","display_name":"Z.AI: GLM 5.3 Prime","description":"GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token context window and up to 128K output tokens, and targets coding and agentic workloads, including long-horizon multi-turn agent orchestration, real-time conversation, and streaming code generation.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.4,"min_completion_price":4.4,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"glm-5.3-prime","prompt_price":1.4,"completion_price":4.4,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"moonshotai/kimi-k3","object":"model","created":1626777600,"model_id":"moonshotai/kimi-k3","canonical_slug":"moonshotai/kimi-k3","display_name":"Moonshotai: Kimi K3","description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.","model_family":"Kimi","model_family_id":27,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":1048576,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.4135,"min_completion_price":7.0665,"supported_endpoint_types":["openai"],"provider_count":8,"providers":[{"provider_slug":"alibaba/cn/flex","service_tier":"flex","endpoint_name":"kimi-k3","prompt_price":1.4135,"completion_price":7.0665,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/hk","service_tier":"standard","endpoint_name":"kimi-k3","prompt_price":1.4135,"completion_price":7.0665,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/eu","service_tier":"standard","endpoint_name":"kimi-k3","prompt_price":1.4135,"completion_price":7.0665,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/jp","service_tier":"standard","endpoint_name":"kimi-k3","prompt_price":1.4135,"completion_price":7.0665,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"kimi-k3","prompt_price":1.5,"completion_price":7.5,"context_length":1048576,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"moonshotai","service_tier":"standard","endpoint_name":"kimi-k3","prompt_price":3,"completion_price":15,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"MXFP4"},{"provider_slug":"fireworks","service_tier":"standard","endpoint_name":"accounts/fireworks/models/kimi-k3","prompt_price":3,"completion_price":15,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"fireworks/priority","service_tier":"priority","endpoint_name":"accounts/fireworks/models/kimi-k3","prompt_price":3.75,"completion_price":18.75,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"heabsy/cyberheabsy","object":"model","created":1626777600,"model_id":"heabsy/cyberheabsy","canonical_slug":"heabsy/cyberheabsy","display_name":"Heabsy: Cyber Heabsy","description":"A low-refusal text model for authorized security research, roleplay, and creative writing. It preserves tool calling after refusal removal, supports optional reasoning, and has a 1M-token context window.","model_family":"Heabsy","model_family_id":129,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.4286,"min_completion_price":4.2857,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"heabsy","service_tier":"standard","endpoint_name":"cyberheabsy","prompt_price":1.4286,"completion_price":4.2857,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"nvfp4"}]},{"id":"x-ai/grok-4.5","object":"model","created":1626777600,"model_id":"x-ai/grok-4.5","canonical_slug":"x-ai/grok-4.5","display_name":"xAI: Grok 4.5","description":"Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","model_family":"Grok","model_family_id":20,"category_type":"LLM","context_length":500000,"max_input_tokens":500000,"max_output_tokens":500000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.6,"min_completion_price":4.8,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-4.5","prompt_price":1.6,"completion_price":4.8,"context_length":500000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"x-ai/grok-4.6","object":"model","created":1626777600,"model_id":"x-ai/grok-4.6","canonical_slug":"x-ai/grok-4.6","display_name":"xAI: Grok 4.6","description":"Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","model_family":"Grok","model_family_id":20,"category_type":"LLM","context_length":500000,"max_input_tokens":500000,"max_output_tokens":500000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.6,"min_completion_price":4.8,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-4.6","prompt_price":1.6,"completion_price":4.8,"context_length":500000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"moonshotai/kimi-v1-128k","object":"model","created":1626777600,"model_id":"moonshotai/kimi-v1-128k","canonical_slug":"moonshotai/kimi-v1-128k","display_name":"Moonshot: Kimi V1 128K","description":" Kimi v1 (also marketed as the moonshot‑v1 family) is a large‑scale Transformer‑based language model developed by Moonshot AI that pushes the frontier of long‑context and multimodal AI by offering a maximum context window of 128 k tokens (roughly 200 k Chinese characters), automatically scaling to 8 k or 32 k modes for cost‑effective inference, and integrating visual understanding to process images directly; its core capabilities include extracting and summarizing massive documents in a single pass, generating structured outputs such as precise JSON through a dedicated JSON‑Mode, invoking external tools via ToolCalls, streaming partial results with Partial‑Mode, and performing real‑time internet searches to augment responses, while an auto‑context cache reduces token‑billing to just ¥1 per million cached tokens; technically, Kimi v1 leverages a ~2 trillion‑parameter Transformer architecture refined with reinforcement‑learning and long‑Chain‑of‑Thought (Long‑CoT) techniques, enabling high‑fidelity reasoning over ultra‑long texts, low‑latency token reuse, and robust multimodal perception, positioning it as one of the most advanced domestic LLMs for enterprise and developer applications.","model_family":"Kimi","model_family_id":27,"model_version":"1","category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":2,"min_completion_price":5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"moonshotai","service_tier":"standard","endpoint_name":"moonshot-v1-128k","prompt_price":2,"completion_price":5,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-sonnet-5","object":"model","created":1626777600,"model_id":"anthropic/claude-sonnet-5","canonical_slug":"anthropic/claude-sonnet-5","display_name":"Anthropic: Claude Sonnet 5","description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":1000000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":2,"min_completion_price":10,"supported_endpoint_types":["anthropic","openai"],"provider_count":2,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-sonnet-5","prompt_price":2,"completion_price":10,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-sonnet-5","prompt_price":2,"completion_price":10,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.6-sol","object":"model","created":1626777600,"model_id":"openai/gpt-5.6-sol","canonical_slug":"openai/gpt-5.6-sol","display_name":"OpenAI: GPT-5.6 Sol","description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":2,"min_completion_price":10,"supported_endpoint_types":["openai"],"provider_count":4,"providers":[{"provider_slug":"openai/flex","service_tier":"flex","endpoint_name":"gpt-5.6-sol","prompt_price":2,"completion_price":10,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5.6-sol","prompt_price":3.75,"completion_price":22.5,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-5.6-sol","prompt_price":4,"completion_price":20,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai/priority","service_tier":"priority","endpoint_name":"gpt-5.6-sol","prompt_price":8,"completion_price":40,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"sakana/fugu-max-v1.0","object":"model","created":1626777600,"model_id":"sakana/fugu-max-v1.0","canonical_slug":"sakana/fugu-max-v1.0","display_name":"Sakana: Fugu Max V1.0","description":"Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route tasks across a fixed pool of open-weights and specialized models, including NVIDIA's Nemotron family, and to recursively call instances of itself.\n\nFugu Max dynamically selects efficient combinations of expert agents to improve quality and cost together, and is priced flat regardless of context length. It supports configurable reasoning effort (high, xhigh, max), function calling, structured outputs, image and PDF input, and built-in web search and web fetch. Orchestration tokens consumed by the system are billed as standard input/output tokens.","model_family":"Fugu","model_family_id":111,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":2,"min_completion_price":6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"sakana","service_tier":"standard","endpoint_name":"fugu-max-v1.0","prompt_price":2,"completion_price":6,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"x-ai/grok-4.7","object":"model","created":1626777600,"model_id":"x-ai/grok-4.7","canonical_slug":"x-ai/grok-4.7","display_name":"xAI: Grok 4.7","description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and managing long context, and it improves on its predecessor at professional knowledge work such as drafting documents and presentations.\n\nThe model was trained with a longer reinforcement learning run weighted toward problems that take many hours to complete, and natively understands the Grok Bot harness for conversational tasks. It ships with a new safeguard stack that pairs strong jailbreak resistance with low refusal rates for legitimate cybersecurity and biology work. SpaceXAI's reported benchmark results use the xhigh reasoning effort.","model_family":"Grok","model_family_id":20,"category_type":"LLM","context_length":500000,"max_input_tokens":500000,"max_output_tokens":500000,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":2,"min_completion_price":6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-4.7","prompt_price":2,"completion_price":6,"context_length":500000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"qwen/qwen3.8-max-prime","object":"model","created":1626777600,"model_id":"qwen/qwen3.8-max-prime","canonical_slug":"qwen/qwen3.8-max-prime","display_name":"Qwen: Qwen3.8 Max Prime","description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default. Tool calling, structured outputs, and configurable reasoning effort are supported, matching Qwen3.8 Max.","model_family":"Qwen","model_family_id":49,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","video"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":2,"min_completion_price":6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen3.8-max-prime","prompt_price":2,"completion_price":6,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-sonnet-5.5","object":"model","created":1626777600,"model_id":"anthropic/claude-sonnet-5.5","canonical_slug":"anthropic/claude-sonnet-5.5","display_name":"Claude Sonnet 5.5","description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":2,"min_completion_price":10,"supported_endpoint_types":["anthropic","openai"],"provider_count":2,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-sonnet-5-5","prompt_price":2,"completion_price":10,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-sonnet-5-5","prompt_price":2,"completion_price":10,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-4.5x","object":"model","created":1626777600,"model_id":"z-ai/glm-4.5x","canonical_slug":"z-ai/glm-4.5x","display_name":"Z.AI: GLM 4.5X","description":"GLM-4.5 and GLM-4.5-Air are our latest flagship models, purpose-built as foundational models for agent-oriented applications. Both leverage a Mixture-of-Experts (MoE) architecture. GLM-4.5 has a total parameter count of 355B with 32B active parameters per forward pass, while GLM-4.5-Air adopts a more streamlined design with 106B total parameters and 12B active parameters.\nBoth models share a similar training pipeline: an initial pretraining phase on 15 trillion tokens of general-domain data, followed by targeted fine-tuning on datasets covering code, reasoning, and agent-specific tasks. The context length has been extended to 128k tokens, and reinforcement learning was applied to further enhance reasoning, coding, and agent performance.\nGLM-4.5 and GLM-4.5-Air are optimized for tool invocation, web browsing, software engineering, and front-end development. They can be integrated into code-centric agents such as Claude Code and Roo Code, and also support arbitrary agent applications through tool invocation APIs.\nBoth models support hybrid reasoning modes, offering two execution modes: Thinking Mode for complex reasoning and tool usage, and Non-Thinking Mode for instant responses. These modes can be toggled via the thinking.typeparameter (with enabled and disabled settings), and dynamic thinking is enabled by default.","model_family":"GLM","model_family_id":17,"model_version":"4.5x","category_type":"LLM","context_length":128000,"max_input_tokens":128000,"max_output_tokens":96000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":2.2,"min_completion_price":8.9,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"z-ai","service_tier":"standard","endpoint_name":"glm-4.5-x","prompt_price":2.2,"completion_price":8.9,"context_length":128000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"xiaomi/mimo-v2.6-flash-uncensored","object":"model","created":1626777600,"model_id":"xiaomi/mimo-v2.6-flash-uncensored","canonical_slug":"xiaomi/mimo-v2.6-flash-uncensored","display_name":"Xiaomi: MiMo V2.6 Flash Uncensored","description":"A lower-refusal MiMo V2.6 Flash finetune with image input, a 1M-token context window, separate reasoning output, and tool calling.","model_family":"Mimo","model_family_id":35,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":65536,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":2.202,"min_completion_price":7.1425,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"heabsy","service_tier":"standard","endpoint_name":"mimo-v26-flash-unc","prompt_price":2.202,"completion_price":7.1425,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"nvfp4"}]},{"id":"cohere/command-a-03-2025","object":"model","created":1626777600,"model_id":"cohere/command-a-03-2025","canonical_slug":"cohere/command-a-03-2025","display_name":"Cohere: Command A 03-2025","description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases.\nCompared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.","model_family":"Cohere","model_family_id":64,"category_type":"LLM","context_length":256000,"max_input_tokens":256000,"max_output_tokens":8200,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":2.5,"min_completion_price":10,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"cohere","service_tier":"standard","endpoint_name":"command-a-03-2025","prompt_price":2.5,"completion_price":10,"context_length":256000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"inflection/inflection-3-pi","object":"model","created":1626777600,"model_id":"inflection/inflection-3-pi","canonical_slug":"inflection/inflection-3-pi","display_name":"Inflection: Inflection 3 Pi","description":"Inflection 3 Pi powers Inflection's [Pi](https://pi.ai/) chatbot, including backstory, emotional intelligence, productivity, and safety. It has access to recent news, and excels in scenarios like customer support and roleplay.\n\nPi has been trained to mirror your tone and style, if you use more emojis, so will Pi! Try experimenting with various prompts and conversation styles.","model_family":"inflection","model_family_id":72,"category_type":"LLM","context_length":8000,"max_input_tokens":8000,"max_output_tokens":1000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":2.5,"min_completion_price":10,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"inflection","service_tier":"standard","endpoint_name":"Pi-3.1","prompt_price":2.5,"completion_price":10,"context_length":8000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"unbiased/pareto","object":"model","created":1626777600,"model_id":"unbiased/pareto","canonical_slug":"unbiased/pareto","display_name":"Unbiased: Pareto","description":"Pareto is Unbiased's blended AI service: multiple underlying language models contribute to a request and the service returns one synthesized answer through a single model alias. It is a hosted composite service, not an identified standalone weight checkpoint. The published model card supports text and image inputs; the API returns text and tool calls through OpenAI Chat Completions or Anthropic Messages, including streaming. It can be used for conversational assistance and tool-based workflows. The rolling API identifier remains pareto; a dated model-card edition does not establish a version-pinned endpoint. The configured context window is 1,048,576 tokens and the maximum output is 131,072 tokens, using exact limits confirmed by the user on October 2, 2026; these limits are not stated in the retrieved public specification. Serving quantization remains unspecified.","model_family":"Pareto","model_family_id":128,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":2.5,"min_completion_price":7.5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"unbiased","service_tier":"standard","endpoint_name":"pareto","prompt_price":2.5,"completion_price":7.5,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-sonnet-4.5","object":"model","created":1626777600,"model_id":"anthropic/claude-sonnet-4.5","canonical_slug":"anthropic/claude-sonnet-4.5","display_name":"Anthropic: Claude Sonnet 4.5","description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with improvements across system design, code security, and specification adherence. The model is designed for extended autonomous operation, maintaining task continuity across sessions and providing fact-based progress tracking.\n\nSonnet 4.5 also introduces stronger agentic capabilities, including improved tool orchestration, speculative parallel execution, and more efficient context and memory management. With enhanced context tracking and awareness of token usage across tool calls, it is particularly well-suited for multi-context and long-running workflows. Use cases span software engineering, cybersecurity, financial analysis, research agents, and other domains requiring sustained reasoning and tool use.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":1000000,"max_input_tokens":65536,"max_output_tokens":65536,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":3,"min_completion_price":15,"supported_endpoint_types":["anthropic","openai"],"provider_count":2,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-sonnet-4-5-20250929-v1:0","prompt_price":3,"completion_price":15,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-sonnet-4-5-20250929","prompt_price":3,"completion_price":15,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-sonnet-4.6","object":"model","created":1626777600,"model_id":"anthropic/claude-sonnet-4.6","canonical_slug":"anthropic/claude-sonnet-4.6","display_name":"Anthropic: Claude Sonnet 4.6","description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.","model_family":"Claude","model_family_id":5,"model_version":"4.6","category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":3,"min_completion_price":15,"supported_endpoint_types":["anthropic","openai"],"provider_count":4,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-sonnet-4-6","prompt_price":3,"completion_price":15,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"amazon-bedrock/us","service_tier":"standard","endpoint_name":"global.anthropic.claude-sonnet-4-6","prompt_price":3,"completion_price":15,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-sonnet-4-6","prompt_price":3,"completion_price":15,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"claude-platform-aws","service_tier":"standard","endpoint_name":"claude-sonnet-4-6","prompt_price":3,"completion_price":15,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"aion-labs/aion-3.0","object":"model","created":1626777600,"model_id":"aion-labs/aion-3.0","canonical_slug":"aion-labs/aion-3.0","display_name":"AionLabs: Aion 3.0","description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.","model_family":"AionLabs","model_family_id":1,"category_type":"LLM","context_length":131072,"max_input_tokens":131072,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":3,"min_completion_price":6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"aion-labs","service_tier":"standard","endpoint_name":"aion-labs/aion-3.0","prompt_price":3,"completion_price":6,"context_length":131072,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"abliteration-ai/abliterated-model-large-v2","object":"model","created":1626777600,"model_id":"abliteration-ai/abliterated-model-large-v2","canonical_slug":"abliteration-ai/abliterated-model-large-v2","display_name":"Abliterated Large v2","description":"Abliterated Large v2 served by Abliteration.","model_family":"Abliteration","model_family_id":123,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":999990,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":3,"min_completion_price":5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"abliteration","service_tier":"standard","endpoint_name":"abliterated-model-large-v2","prompt_price":3,"completion_price":5,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"abliteration-ai/abliterated-model-large","object":"model","created":1626777600,"model_id":"abliteration-ai/abliterated-model-large","canonical_slug":"abliteration-ai/abliterated-model-large","display_name":"Abliterated Large","description":"Abliterated Large served by Abliteration.","model_family":"Abliteration","model_family_id":123,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":999990,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":3,"min_completion_price":5,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"abliteration","service_tier":"standard","endpoint_name":"abliterated-model-large","prompt_price":3,"completion_price":5,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"}]},{"id":"aion-labs/aion-3.5","object":"model","created":1626777600,"model_id":"aion-labs/aion-3.5","canonical_slug":"aion-labs/aion-3.5","display_name":"AionLabs: Aion 3.5","description":"Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute to a response, producing stronger narrative structure and more compelling tension and conflict.","model_family":"AionLabs","model_family_id":1,"category_type":"LLM","context_length":262144,"max_input_tokens":262144,"max_output_tokens":32768,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":3,"min_completion_price":6,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"aion-labs","service_tier":"standard","endpoint_name":"aion-labs/aion-3.5","prompt_price":3,"completion_price":6,"context_length":262144,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-opus-5.5","object":"model","created":1626777600,"model_id":"anthropic/claude-opus-5.5","canonical_slug":"anthropic/claude-opus-5.5","display_name":"Claude Opus 5.5","description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.\n\nThe model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":4,"min_completion_price":20,"supported_endpoint_types":["anthropic","openai"],"provider_count":3,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-opus-5.5","prompt_price":4,"completion_price":20,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"amazon-bedrock/us","service_tier":"standard","endpoint_name":"global.anthropic.claude-opus-5.5","prompt_price":4,"completion_price":20,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-opus-5-5","prompt_price":4,"completion_price":20,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"xiaomi/mimo-v2.6-pro-ultraspeed","object":"model","created":1626777600,"model_id":"xiaomi/mimo-v2.6-pro-ultraspeed","canonical_slug":"xiaomi/mimo-v2.6-pro-ultraspeed","display_name":"Xiaomi: Mimo V2.6 Pro Ultraspeed","description":"MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x the output speed. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers top-tier performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.","model_family":"Mimo","model_family_id":35,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":4.35,"min_completion_price":8.7,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xiaomi","service_tier":"standard","endpoint_name":"mimo-v2.6-pro-ultraspeed","prompt_price":4.35,"completion_price":8.7,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-opus-4.8","object":"model","created":1626777600,"model_id":"anthropic/claude-opus-4.8","canonical_slug":"anthropic/claude-opus-4.8","display_name":"Anthropic: Claude Opus 4.8","description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.\n\nIt is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":5,"min_completion_price":25,"supported_endpoint_types":["anthropic","openai"],"provider_count":4,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-opus-4-8","prompt_price":5,"completion_price":25,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"amazon-bedrock/eu","service_tier":"standard","endpoint_name":"global.anthropic.claude-opus-4-8","prompt_price":5,"completion_price":25,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"amazon-bedrock/us","service_tier":"standard","endpoint_name":"global.anthropic.claude-opus-4-8","prompt_price":5,"completion_price":25,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-opus-4-8","prompt_price":5,"completion_price":25,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"sakana/fugu-ultra","object":"model","created":1626777600,"model_id":"sakana/fugu-ultra","canonical_slug":"sakana/fugu-ultra","display_name":"Sakana: Fugu Ultra","description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route tasks across a swappable pool of underlying models and to recursively call instances of itself.\n\nFugu Ultra prioritizes answer quality on complex, multi-step reasoning, coding, and agentic workflows. It supports configurable reasoning effort, tool calling, and built-in web search. Orchestration tokens consumed by the system are billed as standard input/output tokens.","model_family":"Fugu","model_family_id":111,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":5,"min_completion_price":30,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"sakana","service_tier":"standard","endpoint_name":"fugu-ultra","prompt_price":5,"completion_price":30,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-opus-5","object":"model","created":1626777600,"model_id":"anthropic/claude-opus-5","canonical_slug":"anthropic/claude-opus-5","display_name":"Claude Opus 5","description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\n\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":5,"min_completion_price":25,"supported_endpoint_types":["anthropic","openai"],"provider_count":3,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-opus-5","prompt_price":5,"completion_price":25,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-opus-5","prompt_price":5,"completion_price":25,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"claude-platform-aws","service_tier":"standard","endpoint_name":"claude-opus-5","prompt_price":5,"completion_price":25,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-6-astra","object":"model","created":1626777600,"model_id":"openai/gpt-6-astra","canonical_slug":"openai/gpt-6-astra","display_name":"OpenAI: GPT-6 Astra","description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon agentic tasks that involve computer and browser use.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":5,"min_completion_price":25,"supported_endpoint_types":["openai"],"provider_count":5,"providers":[{"provider_slug":"openai/flex","service_tier":"flex","endpoint_name":"gpt-6-astra","prompt_price":5,"completion_price":25,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-6-astra","prompt_price":7.5,"completion_price":37.5,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-6-astra","prompt_price":10,"completion_price":50,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai/priority","service_tier":"priority","endpoint_name":"gpt-6-astra","prompt_price":20,"completion_price":100,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"openai/ultrafast","service_tier":"priority","endpoint_name":"gpt-6-astra","prompt_price":60,"completion_price":300,"context_length":1050000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"sakana/fugu-ultra-v2.0","object":"model","created":1626777600,"model_id":"sakana/fugu-ultra-v2.0","canonical_slug":"sakana/fugu-ultra-v2.0","display_name":"Sakana: Fugu Ultra V2.0","description":"Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route tasks across a fixed pool of open and specialized models and to recursively call instances of itself.\n\nFugu Ultra v2 prioritizes answer quality on complex multi-step reasoning, autonomous research, and full-stack software development, and does not rely on individual proprietary frontier models in its pool. It supports configurable reasoning effort (high, xhigh, max), function calling, structured outputs, image and PDF input, and built-in web search. Prompts above 272K tokens are billed at a higher rate. Orchestration tokens consumed by the system are billed as standard input/output tokens.","model_family":"Fugu","model_family_id":111,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":5,"min_completion_price":30,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"sakana","service_tier":"standard","endpoint_name":"fugu-ultra-v2.0","prompt_price":5,"completion_price":30,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-5.3-uncensored","object":"model","created":1626777600,"model_id":"z-ai/glm-5.3-uncensored","canonical_slug":"z-ai/glm-5.3-uncensored","display_name":"Z.AI: GLM 5.3 Uncensored","description":"GLM 5.3 Abliterated is Arnict's modified-refusal-behavior derivative of GLM 5.3, served through the zai/glm-5.3-uncensored endpoint for general-purpose text inference. Arnict's model page describes a mixture-of-experts architecture with DeepSeek Sparse Attention, 78 transformer layers and approximately 753B total parameters. The live catalog declares text-only input and output, a 1,048,576-token context and a 131,072-token output limit. It does not identify a derivative checkpoint, serving quantization or supported generation parameters; the base release's FP8 format is therefore not asserted for this hosted endpoint.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":131072,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":6,"min_completion_price":10,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"hai","service_tier":"priority","endpoint_name":"glm-5.3-uncensored","prompt_price":6,"completion_price":10,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny","quantization":"fp8"},{"provider_slug":"arnict","service_tier":"standard","endpoint_name":"zai/glm-5.3-uncensored","prompt_price":6.25,"completion_price":11.25,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"z-ai/glm-5.3-abliterated","object":"model","created":1626777600,"model_id":"z-ai/glm-5.3-abliterated","canonical_slug":"z-ai/glm-5.3-abliterated","display_name":"Z.AI: GLM 5.3 Abliterated","description":"GLM 5.3 Abliterated is a derivative of the GLM-5.3 open-weight language model, with weight-level modifications intended to reduce refusal behavior. It supports text conversation, reasoning and tool calling for coding, cybersecurity research and agent workflows. Long-context text processing supports working with extensive code, technical documentation and multi-step task histories.\n\n    Applicable scenarios include code analysis, authorized security testing, AI red-team evaluation and agent behavior testing. Tool calling allows a surrounding application to execute functions and return results for subsequent reasoning. The model focuses on complex coding and cybersecurity tasks involving multi-step reasoning.","model_family":"GLM","model_family_id":17,"category_type":"LLM","context_length":1048576,"max_input_tokens":1048576,"max_output_tokens":16384,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":6,"min_completion_price":9,"provider_count":1,"providers":[{"provider_slug":"refuseless","service_tier":"standard","endpoint_name":"glm-5.3-abliterated","prompt_price":6,"completion_price":9,"context_length":1048576,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-opus-4.8-fast","object":"model","created":1626777600,"model_id":"anthropic/claude-opus-4.8-fast","canonical_slug":"anthropic/claude-opus-4.8-fast","display_name":"Anthropic: Claude Opus 4.8 (Fast)","description":"Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed at premium 6x pricing.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":10,"min_completion_price":50,"supported_endpoint_types":["anthropic","openai"],"provider_count":1,"providers":[{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-opus-4-8","prompt_price":10,"completion_price":50,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-fable-5","object":"model","created":1626777600,"model_id":"anthropic/claude-fable-5","canonical_slug":"anthropic/claude-fable-5","display_name":"Anthropic: Claude Fable 5","description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.\n\nIt is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":10,"min_completion_price":50,"supported_endpoint_types":["anthropic","openai"],"provider_count":3,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-fable-5","prompt_price":10,"completion_price":50,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-fable-5","prompt_price":10,"completion_price":50,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"claude-platform-aws","service_tier":"standard","endpoint_name":"claude-fable-5","prompt_price":10,"completion_price":50,"context_length":1000000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-opus-5-fast","object":"model","created":1626777600,"model_id":"anthropic/claude-opus-5-fast","canonical_slug":"anthropic/claude-opus-5-fast","display_name":"Claude Opus 5 (Fast)","description":"Fast-mode variant of Opus 5 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5.\n\nLearn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":10,"min_completion_price":50,"supported_endpoint_types":["anthropic","openai"],"provider_count":1,"providers":[{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-opus-5","prompt_price":10,"completion_price":50,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-fable-5.1","object":"model","created":1626777600,"model_id":"anthropic/claude-fable-5.1","canonical_slug":"anthropic/claude-fable-5.1","display_name":"Claude Fable 5.1","description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":1000000,"max_input_tokens":1000000,"max_output_tokens":128000,"input_modalities":["text","image","file"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":10,"min_completion_price":50,"supported_endpoint_types":["anthropic","openai"],"provider_count":2,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"global.anthropic.claude-fable-5-1","prompt_price":10,"completion_price":50,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"},{"provider_slug":"anthropic","service_tier":"standard","endpoint_name":"claude-fable-5-1","prompt_price":10,"completion_price":50,"context_length":1000000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/o1","object":"model","created":1626777600,"model_id":"openai/o1","canonical_slug":"openai/o1","display_name":"OpenAI: O1","description":"The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought.\n\nThe o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology. ","model_family":"OpenAI GPT","model_family_id":44,"model_version":"o1","category_type":"LLM","context_length":200000,"max_input_tokens":200000,"max_output_tokens":32800,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":false,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":11.25,"min_completion_price":45,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"o1","prompt_price":11.25,"completion_price":45,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"anthropic/claude-opus-4.1","object":"model","created":1626777600,"model_id":"anthropic/claude-opus-4.1","canonical_slug":"anthropic/claude-opus-4.1","display_name":"Anthropic: Claude Opus 4.1","description":"Claude Opus 4-1 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in software engineering, achieving leading results on SWE-bench (72.5%) and Terminal-bench (43.2%). Opus 4 supports extended, agentic workflows, handling thousands of task steps continuously for hours without degradation.","model_family":"Claude","model_family_id":5,"category_type":"LLM","context_length":200000,"max_input_tokens":200000,"max_output_tokens":32000,"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":15,"min_completion_price":75,"supported_endpoint_types":["anthropic","openai"],"provider_count":1,"providers":[{"provider_slug":"amazon-bedrock","service_tier":"standard","endpoint_name":"us.anthropic.claude-opus-4-1-20250805-v1:0","prompt_price":15,"completion_price":75,"context_length":200000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/tts-1/text-to-audio","object":"model","created":1626777600,"model_id":"openai/tts-1/text-to-audio","canonical_slug":"openai/tts-1/text-to-audio","display_name":"OpenAI: TTS-1 (Text to Audio)","description":"TTS is a model that converts text to natural sounding speech. TTS is optimized for realtime or interactive scenarios. For offline scenarios, TTS-HD provides higher quality. The API supports six different voices.\n\nMax request data size: 4,096 chars can be converted from text to speech per API request.","model_family":"OpenAI","model_family_id":43,"model_version":"1","category_type":"Text To Speech","context_length":10000,"max_input_tokens":10000,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["audio"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":15,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"tts","prompt_price":15,"completion_price":null,"context_length":10000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-5.4-pro","object":"model","created":1626777600,"model_id":"openai/gpt-5.4-pro","canonical_slug":"openai/gpt-5.4-pro","display_name":"OpenAI: GPT-5.4 Pro","description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"LLM","context_length":1050000,"max_input_tokens":1050000,"max_output_tokens":128000,"input_modalities":["text"],"output_modalities":["text"],"supports_streaming":true,"supports_function_calling":true,"supports_vision":true,"supports_json_mode":true,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":22.5,"min_completion_price":135,"supported_endpoint_types":["openai-response"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-5.4-pro","prompt_price":22.5,"completion_price":135,"context_length":1050000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/tts-1-hd/text-to-audio","object":"model","created":1626777600,"model_id":"openai/tts-1-hd/text-to-audio","canonical_slug":"openai/tts-1-hd/text-to-audio","display_name":"OpenAI: TTS-1-HD (Text to Audio)","description":"TTS-HD is a model that converts text to natural sounding speech. TTS is optimized for realtime or interactive scenarios. For offline scenarios, TTS-HD provides higher quality. The API supports six different voices.\n\nMax request data size: 4,096 chars can be converted from text to speech per API request.","model_family":"OpenAI","model_family_id":43,"category_type":"Text To Speech","context_length":10000,"max_input_tokens":10000,"max_output_tokens":10000,"input_modalities":["text"],"output_modalities":["audio"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":33,"min_completion_price":null,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"tts-hd","prompt_price":33,"completion_price":null,"context_length":10000,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/nano-banana/text-to-image","object":"model","created":1626777600,"model_id":"google/nano-banana/text-to-image","canonical_slug":"google/nano-banana/text-to-image","display_name":"Google: Nano Banana (Text to Image)","description":"Google's famous original image generation and editing model","model_family":"Gemini","model_family_id":15,"category_type":"Text to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.225,"min_completion_price":22.5,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-2.5-flash-image","prompt_price":0.225,"completion_price":22.5,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-2.5-flash-image","prompt_price":0.3,"completion_price":30,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"google/nano-banana/image-to-image","object":"model","created":1626777600,"model_id":"google/nano-banana/image-to-image","canonical_slug":"google/nano-banana/image-to-image","display_name":"Google: Nano Banana (Image to Image)","description":"Google's famous original image generation and editing model.","model_family":"Gemini","model_family_id":15,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.225,"min_completion_price":22.5,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-2.5-flash-image","prompt_price":0.225,"completion_price":22.5,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-2.5-flash-image","prompt_price":0.3,"completion_price":30,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"google/nano-banana-2-lite/text-to-image","object":"model","created":1626777600,"model_id":"google/nano-banana-2-lite/text-to-image","canonical_slug":"google/nano-banana-2-lite/text-to-image","display_name":"Google: Nano Banana 2 Lite (Text to Image)","description":"Google Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) delivers Pro-quality image generation at Flash speed with 512px to 4K resolution support. Features include improved text rendering, character consistency for up to 5 characters, and real-world knowledge integration.","model_family":"Gemini","model_family_id":15,"category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.1875,"min_completion_price":22.5,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3.1-flash-lite-image","prompt_price":0.1875,"completion_price":22.5,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-3.1-flash-lite-image","prompt_price":0.25,"completion_price":30,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"google/nano-banana-2/text-to-image","object":"model","created":1626777600,"model_id":"google/nano-banana-2/text-to-image","canonical_slug":"google/nano-banana-2/text-to-image","display_name":"Google: Nano Banana 2 (Text to Image)","description":"Google Nano Banana 2 (Gemini 3.1 Flash Image) delivers Pro-quality image generation at Flash speed with 512px to 4K resolution support. Features include improved text rendering, character consistency for up to 5 characters, and real-world knowledge integration. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.","model_family":"Gemini","model_family_id":15,"category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.375,"min_completion_price":45,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3.1-flash-image","prompt_price":0.375,"completion_price":45,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-3.1-flash-image","prompt_price":0.5,"completion_price":60,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"google/nano-banana-2-lite/image-to-image","object":"model","created":1626777600,"model_id":"google/nano-banana-2-lite/image-to-image","canonical_slug":"google/nano-banana-2-lite/image-to-image","display_name":"Google: Nano Banana 2 Lite (Image to Image)","description":"Nano Banana 2 Lite is Google's new state-of-the-art image generation and editing model.","model_family":"Gemini","model_family_id":15,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.1875,"min_completion_price":22.5,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3.1-flash-lite-image","prompt_price":0.1875,"completion_price":22.5,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-3.1-flash-lite-image","prompt_price":0.25,"completion_price":30,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"google/nano-banana-2/image-to-image","object":"model","created":1626777600,"model_id":"google/nano-banana-2/image-to-image","canonical_slug":"google/nano-banana-2/image-to-image","display_name":"Google: Nano Banana 2 (Image to Image)","description":"Nano Banana 2 is Google's new state-of-the-art image generation and editing model.","model_family":"Gemini","model_family_id":15,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0.375,"min_completion_price":45,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3.1-flash-image","prompt_price":0.375,"completion_price":45,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-3.1-flash-image","prompt_price":0.5,"completion_price":60,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"google/nano-banana-pro/text-to-image","object":"model","created":1626777600,"model_id":"google/nano-banana-pro/text-to-image","canonical_slug":"google/nano-banana-pro/text-to-image","display_name":"Google: Nano Banana Pro (Text to Image)","description":"Google's Nano Banana pro (Gemini 3.0 Pro Image) is a cutting-edge text-to-image model enabling high-res 4K image generation optimized for phones. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.","model_family":"Gemini","model_family_id":15,"category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.5,"min_completion_price":90,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3-pro-image","prompt_price":1.5,"completion_price":90,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-3-pro-image","prompt_price":2,"completion_price":120,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"google/nano-banana-pro/image-to-image","object":"model","created":1626777600,"model_id":"google/nano-banana-pro/image-to-image","canonical_slug":"google/nano-banana-pro/image-to-image","display_name":"Google: Nano Banana Pro (Image to Image)","description":"Google Nano Banana Pro (Gemini 3.0 Pro Image) Edit enables image editing with 4K-capable output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.","model_family":"Gemini","model_family_id":15,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":1.5,"min_completion_price":90,"supported_endpoint_types":["gemini","openai"],"provider_count":2,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"gemini-3-pro-image","prompt_price":1.5,"completion_price":90,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"google-ai-studio","service_tier":"standard","endpoint_name":"gemini-3-pro-image","prompt_price":2,"completion_price":120,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"x-ai/grok-imagine-image/text-to-image","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-image/text-to-image","canonical_slug":"x-ai/grok-imagine-image/text-to-image","display_name":"xAI: Grok Imagine Image (Text to Image)","description":"Generate highly aesthetic images with xAI's Grok Imagine Image generation model.","model_family":"Grok","model_family_id":20,"category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.016,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-image","prompt_price":null,"completion_price":null,"request_price":0.016,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"unknown"}]},{"id":"x-ai/grok-imagine-image/image-to-image","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-image/image-to-image","canonical_slug":"x-ai/grok-imagine-image/image-to-image","display_name":"xAI: Grok Imagine Image (Image to Image)","description":"Edit images precisely with xAI's Grok Imagine model.","model_family":"Grok","model_family_id":20,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.016,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-image","prompt_price":null,"completion_price":null,"request_price":0.016,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"unknown"}]},{"id":"x-ai/grok-imagine-image-quality/text-to-image","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-image-quality/text-to-image","canonical_slug":"x-ai/grok-imagine-image-quality/text-to-image","display_name":"xAI: Grok Imagine Image Quality (Text to Image)","description":"Grok Imagine Pro is an advanced AI model from xAI that creates high-quality visuals from text prompts and allows you to edit or analyze existing images.","model_family":"Grok","model_family_id":20,"category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.04,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-image-quality","prompt_price":null,"completion_price":null,"request_price":0.04,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"unknown"}]},{"id":"x-ai/grok-imagine-image-quality/image-to-image","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-image-quality/image-to-image","canonical_slug":"x-ai/grok-imagine-image-quality/image-to-image","display_name":"xAI: Grok Imagine Image Quality (Image to Image)","description":"Grok Imagine Pro is an advanced AI model from xAI that creates high-quality visuals from text prompts and allows you to edit or analyze existing images.","model_family":"Grok","model_family_id":20,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.04,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-image-quality","prompt_price":null,"completion_price":null,"request_price":0.04,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"unknown"}]},{"id":"openai/gpt-image-2/text-to-image","object":"model","created":1626777600,"model_id":"openai/gpt-image-2/text-to-image","canonical_slug":"openai/gpt-image-2/text-to-image","display_name":"OpenAI: GPT Images 2 (Text to Image)","description":"GPT Image 2, OpenAI's latest image model, is capable of creating extremely detailed images with fine typography.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":3.75,"min_completion_price":22.5,"min_request_price":3.75,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-image-2","prompt_price":3.75,"completion_price":22.5,"request_price":3.75,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-image-2","prompt_price":5,"completion_price":30,"request_price":5,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"openai/gpt-image-2.5-sunburst/text-to-image","object":"model","created":1626777600,"model_id":"openai/gpt-image-2.5-sunburst/text-to-image","canonical_slug":"openai/gpt-image-2.5-sunburst/text-to-image","display_name":"OpenAI: GPT Image 2.5 Sunburst (Text to Image)","description":"OpenAI's precision-focused image model, built for premium visual work, extra fidelity on intricate detail, in exchange for longer generation times.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":3.75,"min_completion_price":22.5,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-image-2.5-sunburst","prompt_price":3.75,"completion_price":22.5,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-image-2.5-sunburst","prompt_price":5,"completion_price":30,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"openai/gpt-image-2.5-flare/text-to-image","object":"model","created":1626777600,"model_id":"openai/gpt-image-2.5-flare/text-to-image","canonical_slug":"openai/gpt-image-2.5-flare/text-to-image","display_name":"OpenAI: GPT Image 2.5 Flare (Text to Image)","description":"OpenAI's default image model for most applications. Fast, high-quality generation with natural lighting, rich textures, and support for complex layouts including transparent backgrounds.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":3.75,"min_completion_price":22.5,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-image-2.5-flare","prompt_price":3.75,"completion_price":22.5,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-image-2.5-flare","prompt_price":5,"completion_price":30,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"openai/gpt-image-2/image-to-image","object":"model","created":1626777600,"model_id":"openai/gpt-image-2/image-to-image","canonical_slug":"openai/gpt-image-2/image-to-image","display_name":"OpenAI: GPT Images 2 (Image to Image)","description":"GPT Image 2, OpenAI's latest image model, is capable of creating extremely detailed images with fine typography.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":3.75,"min_completion_price":22.5,"min_request_price":3.75,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-image-2","prompt_price":3.75,"completion_price":22.5,"request_price":3.75,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-image-2","prompt_price":5,"completion_price":30,"request_price":5,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"openai/gpt-image-2.5-sunburst/image-to-image","object":"model","created":1626777600,"model_id":"openai/gpt-image-2.5-sunburst/image-to-image","canonical_slug":"openai/gpt-image-2.5-sunburst/image-to-image","display_name":"OpenAI: GPT Image 2.5 Sunburst (Image to Image)","description":"Editing built for the tightest control, edits scoped precisely to the instruction, with subject and composition preserved across many rounds of revision.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":3.75,"min_completion_price":22.5,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-image-2.5-sunburst","prompt_price":3.75,"completion_price":22.5,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-image-2.5-sunburst","prompt_price":5,"completion_price":30,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"openai/gpt-image-2.5-flare/image-to-image","object":"model","created":1626777600,"model_id":"openai/gpt-image-2.5-flare/image-to-image","canonical_slug":"openai/gpt-image-2.5-flare/image-to-image","display_name":"OpenAI: GPT Image 2.5 Flare (Image to Image)","description":"Precise image editing that changes only what's asked, keeping subject, composition, and background intact, with reference subjects staying recognizable across styles and successive edits.","model_family":"OpenAI GPT","model_family_id":44,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":3.75,"min_completion_price":22.5,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"azure","service_tier":"standard","endpoint_name":"gpt-image-2.5-flare","prompt_price":3.75,"completion_price":22.5,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"allow"},{"provider_slug":"openai","service_tier":"standard","endpoint_name":"gpt-image-2.5-flare","prompt_price":5,"completion_price":30,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"google/veo3.1/image-to-video","object":"model","created":1626777600,"model_id":"google/veo3.1/image-to-video","canonical_slug":"google/veo3.1/image-to-video","display_name":"Google: Veo 3.1 (Image to Video)","description":"Google Veo 3.1 is an Image-to-Video model that converts images into high-quality videos with native 1080P output for enhanced detail and creative flexibility. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.","model_family":"Veo","model_family_id":59,"model_version":"3.1","category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.15,"supported_endpoint_types":["gemini","openai"],"provider_count":1,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"veo-3.1-generate-001","prompt_price":null,"completion_price":null,"request_price":0.15,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/veo3.1/first-last-frame-to-video","object":"model","created":1626777600,"model_id":"google/veo3.1/first-last-frame-to-video","canonical_slug":"google/veo3.1/first-last-frame-to-video","display_name":"Google: Veo 3.1 (First Last Frame to Video)","description":"Generate videos from a first and last framed using Google's Veo 3.1.","model_family":"Veo","model_family_id":59,"model_version":"3.1","category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.15,"supported_endpoint_types":["gemini","openai"],"provider_count":1,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"veo-3.1-generate-001","prompt_price":null,"completion_price":null,"request_price":0.15,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/veo3.1/video-extend","object":"model","created":1626777600,"model_id":"google/veo3.1/video-extend","canonical_slug":"google/veo3.1/video-extend","display_name":"Google: Veo 3.1 (Video Extend)","description":"Extend and continue Veo 3.1 videos with smooth motion, preserved style, and strong scene coherence. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.","model_family":"Veo","model_family_id":59,"model_version":"3.1","category_type":"Video to Video","input_modalities":["text","video"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.15,"supported_endpoint_types":["gemini","openai"],"provider_count":1,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"veo-3.1-generate-001","prompt_price":null,"completion_price":null,"request_price":0.15,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"google/veo3.1/reference-to-video","object":"model","created":1626777600,"model_id":"google/veo3.1/reference-to-video","canonical_slug":"google/veo3.1/reference-to-video","display_name":"Google: Veo 3.1 (Reference to Video)","description":"Generate Videos from images using Google's Veo 3.1","model_family":"Veo","model_family_id":59,"model_version":"3.1","category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":true,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.15,"supported_endpoint_types":["gemini","openai"],"provider_count":1,"providers":[{"provider_slug":"google-vertex","service_tier":"standard","endpoint_name":"veo-3.1-generate-001","prompt_price":null,"completion_price":null,"request_price":0.15,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"bytedance/seedance-2.0/text-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.0/text-to-video","canonical_slug":"bytedance/seedance-2.0/text-to-video","display_name":"ByteDance: Seedance 2.0 (Text to Video)","description":"ByteDance's most advanced text-to-video model. Cinematic output with native audio, multi-shot editing, real-world physics, and director-level camera control.","model_family":"ByteDance","model_family_id":63,"category_type":"Text to Video","input_modalities":["text"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.08,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260522151733-2tznf","prompt_price":null,"completion_price":null,"request_price":0.08,"context_length":10000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"bytedance/seedance-2.5/text-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.5/text-to-video","canonical_slug":"bytedance/seedance-2.5/text-to-video","display_name":"ByteDance: Seedance 2.5 (Text to Video)","description":"Dreamina Seedance 2.5 generates native 30-second single-shot video at up to 720p from a single text prompt, reasoning about the whole shot at once so motion, lighting, and subject identity stay coherent from first frame to last.","model_family":"ByteDance","model_family_id":63,"category_type":"Text to Video","input_modalities":["text"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.11,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260807212258-88nps","prompt_price":null,"completion_price":null,"request_price":0.11,"context_length":10000,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"deny"}]},{"id":"bytedance/seedance-2.0/image-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.0/image-to-video","canonical_slug":"bytedance/seedance-2.0/image-to-video","display_name":"ByteDance: Seedance 2.0 (Image to Video)","description":"ByteDance's most advanced image-to-video model. Animate still images into cinematic video with synchronized audio, start and end frame control, and motion prompts.","model_family":"ByteDance","model_family_id":63,"category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.08,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260522151733-2tznf","prompt_price":0,"completion_price":0,"request_price":0.08,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedance-2.5/image-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.5/image-to-video","canonical_slug":"bytedance/seedance-2.5/image-to-video","display_name":"ByteDance: Seedance 2.5 (Image to Video)","description":"Dreamina Seedance 2.5 animates a single still into a native 30-second clip at up to 720p, extending one frame into continuous, coherent motion without the drift or stitching of shorter multi-clip workflows.","model_family":"ByteDance","model_family_id":63,"category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.11,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260807212258-88nps","prompt_price":0,"completion_price":0,"request_price":0.11,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedance-2.0/reference-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.0/reference-to-video","canonical_slug":"bytedance/seedance-2.0/reference-to-video","display_name":"ByteDance: Seedance 2.0 (Reference to Video)","description":"ByteDance's most advanced reference-to-video model. Generate video from up to 9 images, 3 videos, and 3 audio clips with native audio and cinematic camera control.","model_family":"ByteDance","model_family_id":63,"category_type":"Image to Video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.08,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260522151733-2tznf","prompt_price":0,"completion_price":0,"request_price":0.08,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedance-2.0/virtual-portrait-reference-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.0/virtual-portrait-reference-to-video","canonical_slug":"bytedance/seedance-2.0/virtual-portrait-reference-to-video","display_name":"ByteDance: Seedance 2.0 (Real Human Reference to Video)","description":"ByteDance's most advanced reference-to-video model. Generate video from up to 9 images, 3 videos, and 3 audio clips with native audio and cinematic camera control.","model_family":"ByteDance","model_family_id":63,"category_type":"Image to Video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.08,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260630213425-wlfbs","prompt_price":0,"completion_price":0,"request_price":0.08,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedance-2.0/fast/virtual-portrait-reference-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.0/fast/virtual-portrait-reference-to-video","canonical_slug":"bytedance/seedance-2.0/fast/virtual-portrait-reference-to-video","display_name":"ByteDance: Seedance 2.0 Fast (Real Human Reference to Video)","description":"ByteDance's most advanced reference-to-video model, fast tier. Lower latency and cost with up to 9 images, 3 videos, and 3 audio clips as inputs.","model_family":"ByteDance","model_family_id":63,"category_type":"Image to Video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.06,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260630213425-wlfbs","prompt_price":0,"completion_price":0,"request_price":0.06,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedance-2.5/reference-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.5/reference-to-video","canonical_slug":"bytedance/seedance-2.5/reference-to-video","display_name":"ByteDance: Seedance 2.5 (Reference to Video)","description":"Dreamina Seedance 2.5 generates video from up to 50 multimodal references images, video, audio, and style inputs, locking a character, set, and palette across a full 30-second take for production-grade consistency.","model_family":"ByteDance","model_family_id":63,"category_type":"Image to Video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.11,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260807212258-88nps","prompt_price":0,"completion_price":0,"request_price":0.11,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedance-2.5/virtual-portrait-reference-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.5/virtual-portrait-reference-to-video","canonical_slug":"bytedance/seedance-2.5/virtual-portrait-reference-to-video","display_name":"ByteDance: Seedance 2.5 (Real Human Reference to Video)","description":"Dreamina Seedance 2.5 generates video from up to 50 multimodal references images, video, audio, and style inputs, locking a character, set, and palette across a full 30-second take for production-grade consistency.","model_family":"ByteDance","model_family_id":63,"category_type":"Image to Video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.11,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260807212258-88nps","prompt_price":0,"completion_price":0,"request_price":0.11,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedance-2.0/fast/text-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.0/fast/text-to-video","canonical_slug":"bytedance/seedance-2.0/fast/text-to-video","display_name":"ByteDance: Seedance 2.0 Fast (Text to Video)","description":"ByteDance's most advanced text-to-video model, fast tier. Lower latency and cost with cinematic output, native audio, multi-shot editing, and director-level camera control.","model_family":"ByteDance","model_family_id":63,"category_type":"Text to Video","input_modalities":["text"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.06,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260522151938-q2tcd","prompt_price":0,"completion_price":0,"request_price":0.06,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedance-2.0/mini/text-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.0/mini/text-to-video","canonical_slug":"bytedance/seedance-2.0/mini/text-to-video","display_name":"ByteDance: Seedance 2.0 Mini (Text to Video)","description":"Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.","model_family":"ByteDance","model_family_id":63,"category_type":"Text to Video","input_modalities":["text"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.04,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260625135108-8tp2k","prompt_price":0,"completion_price":0,"request_price":0.04,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedance-2.0/fast/image-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.0/fast/image-to-video","canonical_slug":"bytedance/seedance-2.0/fast/image-to-video","display_name":"ByteDance: Seedance 2.0 Fast (Image to Video)","description":"ByteDance's most advanced image-to-video model, fast tier. Lower latency and cost with synchronized audio, start and end frame control, and motion prompts.","model_family":"ByteDance","model_family_id":63,"category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.06,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260522151938-q2tcd","prompt_price":0,"completion_price":0,"request_price":0.06,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedance-2.0/mini/image-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.0/mini/image-to-video","canonical_slug":"bytedance/seedance-2.0/mini/image-to-video","display_name":"ByteDance: Seedance 2.0 Mini (Image to Video)","description":"Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.","model_family":"ByteDance","model_family_id":63,"category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.04,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260625135108-8tp2k","prompt_price":0,"completion_price":0,"request_price":0.04,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedance-2.0/fast/reference-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.0/fast/reference-to-video","canonical_slug":"bytedance/seedance-2.0/fast/reference-to-video","display_name":"ByteDance: Seedance 2.0 Fast (Reference to Video)","description":"ByteDance's most advanced reference-to-video model, fast tier. Lower latency and cost with up to 9 images, 3 videos, and 3 audio clips as inputs.","model_family":"ByteDance","model_family_id":63,"category_type":"Image to Video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.06,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260522151938-q2tcd","prompt_price":0,"completion_price":0,"request_price":0.06,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedance-2.0/mini/reference-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.0/mini/reference-to-video","canonical_slug":"bytedance/seedance-2.0/mini/reference-to-video","display_name":"ByteDance: Seedance 2.0 Mini (Reference to Video)","description":"Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.","model_family":"ByteDance","model_family_id":63,"category_type":"Image to Video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.04,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260625135108-8tp2k","prompt_price":0,"completion_price":0,"request_price":0.04,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedance-2.0/mini/virtual-portrait-reference-to-video","object":"model","created":1626777600,"model_id":"bytedance/seedance-2.0/mini/virtual-portrait-reference-to-video","canonical_slug":"bytedance/seedance-2.0/mini/virtual-portrait-reference-to-video","display_name":"ByteDance: Seedance 2.0 Mini (Real Human Reference to Video)","description":"Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.","model_family":"ByteDance","model_family_id":63,"category_type":"Image to Video","input_modalities":["text","image","video","audio"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.04,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260716145448-44mbj","prompt_price":0,"completion_price":0,"request_price":0.04,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"x-ai/grok-imagine-video/text-to-video","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-video/text-to-video","canonical_slug":"x-ai/grok-imagine-video/text-to-video","display_name":"xAI: Grok Imagine Video (Text to Video)","description":"X-AI Grok Imagine Video generates videos from text descriptions using xAI's Grok Imagine Video model. Create high-quality videos with customizable duration, aspect ratio, and resolution.           \n","model_family":"Grok","model_family_id":20,"category_type":"Text to Video","input_modalities":["text"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.07,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-video","prompt_price":0,"completion_price":0,"request_price":0.07,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"unknown"}]},{"id":"x-ai/grok-imagine-video-1.5-lite/text-to-video","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-video-1.5-lite/text-to-video","canonical_slug":"x-ai/grok-imagine-video-1.5-lite/text-to-video","display_name":"xAI: Grok Imagine Video 1.5 Lite (Text to Video)","description":"Generate videos from text prompts using xAI's Grok Imagine Video 1.5 Lite model.","model_family":"Grok","model_family_id":20,"category_type":"Text to Video","input_modalities":["text"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.02,"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-video-1.5-lite","prompt_price":null,"completion_price":null,"request_price":0.02,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"unknown"}]},{"id":"x-ai/grok-imagine-video/image-to-video","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-video/image-to-video","canonical_slug":"x-ai/grok-imagine-video/image-to-video","display_name":"xAI: Grok Imagine Video (Image to Video)","description":"X-AI Grok Imagine Video generates videos from text descriptions using xAI's Grok Imagine Video model. Create high-quality videos with customizable duration, aspect ratio, and resolution.","model_family":"Grok","model_family_id":20,"category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.07,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-video","prompt_price":0,"completion_price":0,"request_price":0.07,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"unknown"}]},{"id":"x-ai/grok-imagine-video-1.5-lite/image-to-video","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-video-1.5-lite/image-to-video","canonical_slug":"x-ai/grok-imagine-video-1.5-lite/image-to-video","display_name":"xAI: Grok Imagine Video 1.5 Lite (Image to Video)","description":"Generate videos from images using xAI's Grok Imagine Video 1.5 Lite model.","model_family":"Grok","model_family_id":20,"category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.02,"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-video-1.5-lite","prompt_price":null,"completion_price":null,"request_price":0.02,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"unknown"}]},{"id":"x-ai/grok-imagine-video/reference-to-video","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-video/reference-to-video","canonical_slug":"x-ai/grok-imagine-video/reference-to-video","display_name":"xAI: Grok Imagine Video (Reference to Video)","description":"X-AI Grok Imagine Video generates videos from text descriptions using xAI's Grok Imagine Video model. Create high-quality videos with customizable duration, aspect ratio, and resolution.","model_family":"Grok","model_family_id":20,"category_type":"Image to Video","input_modalities":["text","image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.07,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-video","prompt_price":0,"completion_price":0,"request_price":0.07,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"unknown"}]},{"id":"x-ai/grok-imagine-video/edit-video","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-video/video-edit","canonical_slug":"x-ai/grok-imagine-video/edit-video","display_name":"xAI: Grok Imagine Video (Edit Video)","description":"Edit videos using xAI's Grok Imagine.","model_family":"Grok","model_family_id":20,"category_type":"Video to Video","input_modalities":["text","video"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.07,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-video","prompt_price":0,"completion_price":0,"request_price":0.07,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"unknown"}]},{"id":"x-ai/grok-imagine-video/extend-video","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-video/video-extend","canonical_slug":"x-ai/grok-imagine-video/extend-video","display_name":"xAI: Grok Imagine Video (Extend Video)","description":"Extend videos with xAI's Grok Imagine video model.","model_family":"Grok","model_family_id":20,"category_type":"Video to Video","input_modalities":["text","video"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":0,"min_completion_price":0,"min_request_price":0.07,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-video","prompt_price":0,"completion_price":0,"request_price":0.07,"is_zdr":true,"allows_distillation":true,"data_collection_policy":"unknown"}]},{"id":"wan/z-image-spicy/text-to-image","object":"model","created":1626777600,"model_id":"wan/z-image-spicy/text-to-image","canonical_slug":"wan/z-image-spicy/text-to-image","display_name":"Wan Spicy: Z-Image Spicy (Text to Image)","description":"Z Image Spicy text-to-image. Square / portrait / landscape compositions, 256–1536px on each side. Integrate this model via REST with endpoint docs, parameters, and code examples.","model_family":"Wan-Spicy","model_family_id":114,"category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.013,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mulerouter","service_tier":"standard","endpoint_name":"z-image-spicy","prompt_price":null,"completion_price":null,"request_price":0.013,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/qwen-image-edit-spicy/image-to-image","object":"model","created":1626777600,"model_id":"wan/qwen-image-edit-spicy/image-to-image","canonical_slug":"wan/qwen-image-edit-spicy/image-to-image","display_name":"Wan Spicy: Qwen Image Edit Spicy (Image to Image)","description":"Qwen Image Edit Spicy. Add, remove, or modify elements in an existing image with text guidance. Integrate this model via REST with endpoint docs, parameters, and code examples.","model_family":"Wan-Spicy","model_family_id":114,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.04,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mulerouter","service_tier":"standard","endpoint_name":"qwen-image-edit-spicy","prompt_price":null,"completion_price":null,"request_price":0.04,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/face-swap/image-to-image","object":"model","created":1626777600,"model_id":"wan/face-swap/image-to-image","canonical_slug":"wan/face-swap/image-to-image","display_name":"Wan Spicy: Face Swap (Image to Image)","description":"Face Swap model. Integrate this model via REST with endpoint docs, parameters, and code examples.","model_family":"Wan-Spicy","model_family_id":114,"category_type":"Image to Image","input_modalities":["image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.013,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mulerouter","service_tier":"standard","endpoint_name":"face-swap","prompt_price":null,"completion_price":null,"request_price":0.013,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/head-swap/image-to-image","object":"model","created":1626777600,"model_id":"wan/head-swap/image-to-image","canonical_slug":"wan/head-swap/image-to-image","display_name":"Wan Spicy: Head Swap (Image to Image)","description":"Head Swap model. Integrate this model via REST with endpoint docs, parameters, and code examples.","model_family":"Wan-Spicy","model_family_id":114,"category_type":"Image to Image","input_modalities":["image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.013,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mulerouter","service_tier":"standard","endpoint_name":"head-swap","prompt_price":null,"completion_price":null,"request_price":0.013,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/wan2.2-i2v-spicy/image-to-video","object":"model","created":1626777600,"model_id":"wan/wan2.2-i2v-spicy/image-to-video","canonical_slug":"wan/wan2.2-i2v-spicy/image-to-video","display_name":"Wan Spicy: Wan 2.2 I2V Spicy (Image to Video)","description":"Image-to-video with WAN 2.2 Spicy. Animate a starting image. 480p or 720p, 5s or 8s clips. Integrate this model via REST with endpoint docs, parameters, and code examples.","model_family":"Wan-Spicy","model_family_id":114,"category_type":"Image to Video","input_modalities":["image"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.04,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mulerouter","service_tier":"standard","endpoint_name":"wan2.2-i2v-spicy","prompt_price":null,"completion_price":null,"request_price":0.04,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/wan2.7-i2v-spicy/image-to-video","object":"model","created":1626777600,"model_id":"wan/wan2.7-i2v-spicy/image-to-video","canonical_slug":"wan/wan2.7-i2v-spicy/image-to-video","display_name":"Wan Spicy: Wan 2.7 I2V Spicy (Image to Video)","description":"Image-to-video with WAN 2.7 Spicy. Animate a starting image with optional driving audio. 720p or 1080p, 2–15 second clips. Integrate this model via REST with endpoint docs, parameters, and code examples.","model_family":"Wan-Spicy","model_family_id":114,"category_type":"Image to Video","input_modalities":["text","image","audio"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.13,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mulerouter","service_tier":"standard","endpoint_name":"wan2.7-i2v-spicy","prompt_price":null,"completion_price":null,"request_price":0.13,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/wan-animate/video-to-video","object":"model","created":1626777600,"model_id":"wan/wan-animate/video-to-video","canonical_slug":"wan/wan-animate/video-to-video","display_name":"Wan Spicy: Wan Animate (Video to Video)","description":"Wan Animate creates a digital-human animation by combining a character image with a reference motion video. Output duration follows the reference video length, with 480p or 720p output, optional style guidance, and deterministic seed control.","model_family":"Wan-Spicy","model_family_id":114,"category_type":"Video to Video","input_modalities":["image","video"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.053,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mulerouter","service_tier":"standard","endpoint_name":"wan-animate","prompt_price":null,"completion_price":null,"request_price":0.053,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/flashvsr/video-super-resolution","object":"model","created":1626777600,"model_id":"wan/flashvsr/video-super-resolution","canonical_slug":"wan/flashvsr/video-super-resolution","display_name":"Wan Spicy: FlashVSR (Video Super Resolution)","description":"FlashVSR super-resolution model, supporting upscaling from 480P/720P/1080P to 2K/4K.","model_family":"Wan-Spicy","model_family_id":114,"category_type":"Video Super Resolution","input_modalities":["video"],"output_modalities":["video"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.016,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"mulerouter","service_tier":"standard","endpoint_name":"flashvsr","prompt_price":null,"completion_price":null,"request_price":0.016,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"wan/wan2.7/text-to-image","object":"model","created":1626777600,"model_id":"wan/wan2.7/text-to-image","canonical_slug":"wan/wan2.7/text-to-image","display_name":"Alibaba: Wan 2.7 Image (Text to Image)","description":"Generate high-quality images from text prompts using the WAN 2.7 model with advanced prompt understanding and detailed output.","model_family":"Wan","model_family_id":62,"category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.01651,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"wan2.7-image","prompt_price":null,"completion_price":null,"request_price":0.018,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"},{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"wan2.7-image","prompt_price":null,"completion_price":null,"request_price":0.01651,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"wan/wan2.7/image-to-image","object":"model","created":1626777600,"model_id":"wan/wan2.7/image-to-image","canonical_slug":"wan/wan2.7/image-to-image","display_name":"Alibaba: Wan 2.7 Image (Image to Image)","description":"Generate high-quality images from image prompts using the WAN 2.7 model with advanced prompt understanding and detailed output.","model_family":"Wan","model_family_id":62,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.01651,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"wan2.7-image","prompt_price":null,"completion_price":null,"request_price":0.018,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"},{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"wan2.7-image","prompt_price":null,"completion_price":null,"request_price":0.01651,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"wan/wan2.7/pro/text-to-image","object":"model","created":1626777600,"model_id":"wan/wan2.7/pro/text-to-image","canonical_slug":"wan/wan2.7/pro/text-to-image","display_name":"Alibaba: Wan 2.7 Image Pro (Text to Image)","description":"Wan2.7–image-pro，supports text to image, text/image to sequential images, image editing, multi-image reference generation, and interactive editing. Delivers enhanced performance in text rendering, subject consistency, and complex instruction following.","model_family":"Wan","model_family_id":62,"category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.04127,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"wan2.7-image-pro","prompt_price":null,"completion_price":null,"request_price":0.045,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"},{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"wan2.7-image-pro","prompt_price":null,"completion_price":null,"request_price":0.04127,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"wan/wan2.7/pro/image-to-image","object":"model","created":1626777600,"model_id":"wan/wan2.7/pro/image-to-image","canonical_slug":"wan/wan2.7/pro/image-to-image","display_name":"Alibaba: Wan 2.7 Image Pro (Image to Image)","description":"Wan2.7–image-pro，supports text to image, text/image to sequential images, image editing, multi-image reference generation, and interactive editing. Delivers enhanced performance in text rendering, subject consistency, and complex instruction following.","model_family":"Wan","model_family_id":62,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":true,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.04127,"supported_endpoint_types":["openai"],"provider_count":2,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"wan2.7-image-pro","prompt_price":null,"completion_price":null,"request_price":0.045,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"},{"provider_slug":"alibaba/cn","service_tier":"standard","endpoint_name":"wan2.7-image-pro","prompt_price":null,"completion_price":null,"request_price":0.04127,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"bytedance/seedream-5.0/text-to-image","object":"model","created":1626777600,"model_id":"bytedance/seedream-5.0/text-to-image","canonical_slug":"bytedance/seedream-5.0/text-to-image","display_name":"ByteDance: Seedream 5.0 Pro (Text to Image)","description":"ByteDance's Seedream 5.0 Pro is flagship text-to-image model, with deep-thinking prompt understanding, native text in 14 languages, and precise control over dense layouts and structured designs.","model_family":"Seedream","model_family_id":52,"model_version":"5.0-pro","category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.045,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260715142428-vst87","prompt_price":null,"completion_price":null,"request_price":0.045,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"bytedance/seedream-5.0/image-to-image","object":"model","created":1626777600,"model_id":"bytedance/seedream-5.0/image-to-image","canonical_slug":"bytedance/seedream-5.0/image-to-image","display_name":"ByteDance: Seedream 5.0 Pro (Image to Image)","description":"ByteDance's Seedream 5.0 Pro is flagship text-to-image model, with deep-thinking prompt understanding, native text in 14 languages, and precise control over dense layouts and structured designs.","model_family":"Seedream","model_family_id":52,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.045,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260715142428-vst87","prompt_price":null,"completion_price":null,"request_price":0.045,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"bytedance/seedream-lite-5.0/text-to-image","object":"model","created":1626777600,"model_id":"bytedance/seedream-lite-5.0/text-to-image","canonical_slug":"bytedance/seedream-lite-5.0/text-to-image","display_name":"ByteDance: Seedream 5.0 Lite (Text to Image)","description":"Text to Image endpoint for the fast Lite version of Seedream 5.0, supporting high quality intelligent text-to-image generation.","model_family":"Seedream","model_family_id":52,"category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.035,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260715142814-7btjs","prompt_price":null,"completion_price":null,"request_price":0.035,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"bytedance/seedream-lite-5.0/image-to-image","object":"model","created":1626777600,"model_id":"bytedance/seedream-lite-5.0/image-to-image","canonical_slug":"bytedance/seedream-lite-5.0/image-to-image","display_name":"ByteDance: Seedream 5.0 Lite (Image to Image)","description":"Text to Image endpoint for the fast Lite version of Seedream 5.0, supporting high quality intelligent text-to-image generation.","model_family":"Seedream","model_family_id":52,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.035,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"byteplus","service_tier":"standard","endpoint_name":"ep-20260715142814-7btjs","prompt_price":null,"completion_price":null,"request_price":0.035,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"qwen/qwen-image-3.0/image-to-image","object":"model","created":1626777600,"model_id":"qwen/qwen-image-3.0/image-to-image","canonical_slug":"qwen/qwen-image-3.0/image-to-image","display_name":"Alibaba: Qwen Image 3.0 (Image to Image)","description":"Generates images from a text prompt at resolutions up to 2048×2048, with automatic prompt rewriting and prompt-guided resolution selection, building on Qwen's strength in complex text rendering and precise prompt adherence","model_family":"Qwen","model_family_id":49,"category_type":"Image to Image","context_length":4500,"max_input_tokens":4500,"input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.018,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen-image-3.0","prompt_price":null,"completion_price":null,"request_price":0.018,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"qwen/qwen-image-3.0/text-to-image","object":"model","created":1626777600,"model_id":"qwen/qwen-image-3.0/text-to-image","canonical_slug":"qwen/qwen-image-3.0/text-to-image","display_name":"Alibaba: Qwen Image 3.0 (Text to Image)","description":"Edits images from one to three reference images and a natural-language instruction, preserving key details such as facial features and identity while applying the requested changes","model_family":"Qwen","model_family_id":49,"model_version":"3.0","category_type":"Text to Image","context_length":4500,"max_input_tokens":4500,"input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.018,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen-image-3.0","prompt_price":null,"completion_price":null,"request_price":0.018,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"qwen/qwen-image-3.0/pro/image-to-image","object":"model","created":1626777600,"model_id":"qwen/qwen-image-3.0/pro/image-to-image","canonical_slug":"qwen/qwen-image-3.0/pro/image-to-image","display_name":"Alibaba: Qwen Image 3.0 Pro (Image to Image)","description":"Qwen Image 3.0 Pro Edit is a professional-grade image editing model that transforms existing images with natural-language instructions, delivering advanced instruction understanding, superior visual quality, and up to 2K output for creative and production workflows.","model_family":"Qwen","model_family_id":49,"category_type":"Image to Image","context_length":4500,"max_input_tokens":4500,"input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.024,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen-image-3.0-pro","prompt_price":null,"completion_price":null,"request_price":0.024,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"qwen/qwen-image-3.0/pro/text-to-image","object":"model","created":1626777600,"model_id":"qwen/qwen-image-3.0/pro/text-to-image","canonical_slug":"qwen/qwen-image-3.0/pro/text-to-image","display_name":"Alibaba: Qwen Image 3.0 Pro (Text to Image)","description":"Qwen Image 3.0 Pro Text-to-Image is a professional-grade image generation model that creates high-quality images from text prompts, with advanced prompt understanding, strong visual quality, and up to 2K output for creative and production workflows.","model_family":"Qwen","model_family_id":49,"category_type":"Text to Image","context_length":4500,"max_input_tokens":4500,"input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.024,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"alibaba/sg","service_tier":"standard","endpoint_name":"qwen-image-3.0-pro","prompt_price":null,"completion_price":null,"request_price":0.024,"is_zdr":false,"allows_distillation":false,"data_collection_policy":"allow"}]},{"id":"x-ai/grok-imagine-image-2.0/text-to-image","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-image-2.0/text-to-image","canonical_slug":"x-ai/grok-imagine-image-2.0/text-to-image","display_name":"xAI: Grok Imagine Image 2.0 (Text to Image)","description":"Generate images from text using xAi's Grok Imagine 2.0 model.","model_family":"Grok","model_family_id":20,"category_type":"Text to Image","input_modalities":["text"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":false,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.032,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-image-2.0","prompt_price":null,"completion_price":null,"request_price":0.032,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]},{"id":"x-ai/grok-imagine-image-2.0/image-to-image","object":"model","created":1626777600,"model_id":"x-ai/grok-imagine-image-2.0/image-to-image","canonical_slug":"x-ai/grok-imagine-image-2.0/image-to-image","display_name":"xAI: Grok Imagine Image 2.0 (Image to Image)","description":"Edit images with xAi's Grok Imagine 2.0 model.","model_family":"Grok","model_family_id":20,"category_type":"Image to Image","input_modalities":["text","image"],"output_modalities":["image"],"supports_streaming":false,"supports_function_calling":false,"supports_vision":true,"supports_json_mode":false,"deprecated":false,"is_display_only":false,"supports_playground":false,"min_prompt_price":null,"min_completion_price":null,"min_request_price":0.032,"supported_endpoint_types":["openai"],"provider_count":1,"providers":[{"provider_slug":"xai","service_tier":"standard","endpoint_name":"grok-imagine-image-2.0","prompt_price":null,"completion_price":null,"request_price":0.032,"is_zdr":false,"allows_distillation":true,"data_collection_policy":"allow"}]}],"success":true}