{"data":[{"id":"google-gemini-3-1-flash-lite-image","name":"gemini-3-1-flash-lite-image","display_name":"Gemini 3.1 Flash Lite Image","description":"A lightweight, fast image-generation variant of the Gemini 3.1 Flash Lite model, optimized for efficient multimodal generation tasks.","creator":"google","family":"gemini","tier":"flash-lite","version":"3-1","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text","video"],"output":["image","text"]},"context_window":65536,"max_output_tokens":58982,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-01","training_data_cutoff":null,"supported_reasoning_efforts":["default","minimal"],"tokenizer":"Gemini","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2026-06-30","earliest_deprecation_date":"2027-06-28","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["databricks/databricks-gemini-3-1-flash-lite-image","gemini-3.1-flash-lite-image","gemini/gemini-3.1-flash-lite-image","google-gemini-3-1-flash-lite-image","google/gemini-3.1-flash-lite-image","openrouter/google/gemini-3.1-flash-lite-image","publishers/google/models/gemini-3.1-flash-lite-image","together_ai/google/flash-image-3.1-lite","vertex_ai/gemini-3.1-flash-lite-image"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-11-22 08:02:29"},{"id":"mistral-mixtral-8x22b-instruct","name":"mistral-mixtral-8x22b-instruct","display_name":"Mixtral 8x22B Instruct","description":"The instruction-tuned version of Mistral AI's Mixtral 8x22B MoE model, optimized for following complex instructions and multi-turn dialogue.","creator":"mistral","family":"mixtral","tier":"","version":null,"type":"language","size_in_bn":22,"modalities":{"input":["pdf","text"],"output":["text"]},"context_window":65536,"max_output_tokens":52428,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-01-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Mistral","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2024-04-17","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/mixtral-8x22b-instruct","anyscale/mistralai/Mixtral-8x22B-Instruct-v0.1","fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct","fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf","huggingface-llm-mistralai-mixtral-8x22B-instruct-v0-1","mistral-8x22b-instruct","mistral-mixtral-8x22b-instruct","mistral/mixtral-8x22b-instruct","mistralai/mixtral-8x22b-instruct","nscale/mistralai/mixtral-8x22b-instruct-v0.1","ollama/mixtral-8x22B-Instruct-v0.1","openrouter/mistralai/mixtral-8x22b-instruct","vercel_ai_gateway/mistral/mixtral-8x22b-instruct"],"hf_likes":748,"hf_downloads":28279,"hf_downloads_all_time":6052030,"hf_trending_score":0,"updated_at":"2026-11-22 08:02:29"},{"id":"alibaba-qwen2-5-7b-instruct","name":"qwen2-5-7b-instruct","display_name":"Qwen2.5 7B Instruct","description":"A 7-billion-parameter instruction-tuned LLM from Alibaba's Qwen2.5 series, optimized for responsive text generation and instruction following.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2024-10-16","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/qwen2p5-7b-instruct","alibaba-qwen2-5-7b-instruct","deepinfra/Qwen/Qwen2.5-7B-Instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-7b-instruct","huggingface-llm-qwen2-5-7b-instruct","novita/qwen/qwen2.5-7b-instruct","openrouter/qwen/qwen-2.5-7b-instruct","qwen/qwen-2.5-7b-instruct","qwen/qwen2.5-7b-instruct","qwen2.5-7b-instruct"],"hf_likes":1217,"hf_downloads":12284868,"hf_downloads_all_time":119351105,"hf_trending_score":9,"updated_at":"2026-11-22 08:02:29"},{"id":"alibaba-qwq-plus","name":"qwq-plus","display_name":"QwQ Plus","description":"An enhanced tier of Alibaba's QwQ reasoning LLM series, offering stronger reasoning performance over the base QwQ model.","creator":"alibaba","family":"qwen","tier":"plus","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":98304,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["alibaba-qwq-plus","dashscope/qwq-plus","qwen_ai_platform/qwq-plus","qwencloud/qwq-plus","qwq-plus"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-11-22 08:02:29"},{"id":"microsoft-wizardlm-2-8x22b","name":"wizardlm-2-8x22b","display_name":"WizardLM 2 8x22B","description":"Microsoft's most capable WizardLM fine-tune built on a Mixtral 8x22B MoE backbone, targeting highly competitive instruction-following and reasoning performance.","creator":"microsoft","family":"wizardlm","tier":"","version":"2","type":"language","size_in_bn":22,"modalities":{"input":["text"],"output":["text"]},"context_window":65536,"max_output_tokens":8000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-04-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Mistral","capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2024-04-16","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["deepinfra/microsoft/WizardLM-2-8x22B","huggingface-llm-alpindale-wizard-lm-2-8-22B","microsoft-wizardlm-2-8x22b","microsoft/wizardlm-2-8x22b","novita/microsoft/wizardlm-2-8x22b","openrouter/microsoft/wizardlm-2-8x22b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-11-22 08:02:29"},{"id":"openai-gpt-audio","name":"gpt-audio","display_name":"GPT Audio","description":"OpenAI's first generally available audio model that accepts and produces audio inputs and outputs via the Chat Completions API.","creator":"openai","family":"gpt-audio","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["audio","text"],"output":["audio","text"]},"context_window":128000,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-10","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-08-28","earliest_deprecation_date":"2027-01-20","deprecated":false,"has_pricing":true,"provider_count":3,"ids":["azure/gpt-audio","azure/gpt-audio-2025-08-28","gpt-audio","gpt-audio-2025-08-28","openai-gpt-audio","openai/gpt-audio","openrouter/openai/gpt-audio"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-11-22 08:02:29"},{"id":"openai-gpt-realtime-1-5","name":"gpt-realtime-1-5","display_name":"GPT Realtime 1.5","description":"OpenAI's flagship audio model for voice agents and customer support, delivering high-quality realtime speech interaction.","creator":"openai","family":"gpt","tier":"","version":"1-5","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","text"],"output":["audio","text"]},"context_window":32000,"max_output_tokens":4096,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-09","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2026-02-23","earliest_deprecation_date":"2027-08-24","deprecated":false,"has_pricing":true,"provider_count":3,"ids":["azure/gpt-realtime-1.5","azure/gpt-realtime-1.5-2026-02-23","azure/us/gpt-realtime-1.5","gpt-realtime-1.5","openai-gpt-realtime-1-5","openai/gpt-realtime-1.5"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-11-22 08:02:29"},{"id":"openai-gpt-realtime-2-1","name":"gpt-realtime-2-1","display_name":"GPT Realtime 2.1","description":"A speech-to-speech realtime LLM from OpenAI with improved alphanumeric recognition, silence handling, and interruption behavior over WebRTC and WebSocket.","creator":"openai","family":"gpt","tier":"","version":"2-1","type":"language","size_in_bn":null,"modalities":{"input":["audio","image","text"],"output":["audio","text"]},"context_window":128000,"max_output_tokens":32000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-09","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":false,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2026-07-09","earliest_deprecation_date":"2027-07-31","deprecated":false,"has_pricing":true,"provider_count":3,"ids":["azure/gpt-realtime-2.1","azure/gpt-realtime-2.1-2026-07-07","azure/us/gpt-realtime-2.1","gpt-realtime-2.1","openai-gpt-realtime-2-1","openai/gpt-realtime-2.1"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-11-22 08:02:29"},{"id":"openai-o1-mini","name":"o1-mini","display_name":"o1 Mini","description":"A faster and more affordable variant of the o1 reasoning model, optimized for STEM tasks while maintaining strong chain-of-thought reasoning capabilities.","creator":"openai","family":"o","tier":"","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"max_output_tokens":65536,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-10","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":false,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2024-09-12","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["azure/eu/o1-mini","azure/eu/o1-mini-2024-09-12","azure/o1-mini","azure/o1-mini-2024-09-12","azure/us/o1-mini","azure/us/o1-mini-2024-09-12","o1-mini","openai-o1-mini","replicate/openai/o1-mini"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-11-22 08:02:29"},{"id":"alibaba-qwen2-5-coder-3b-instruct","name":"qwen2-5-coder-3b-instruct","display_name":"Qwen2.5 Coder 3B Instruct","description":"A 3-billion-parameter instruction-tuned code LLM from Alibaba's Qwen2.5-Coder series, suitable for compact coding assistant applications.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":3,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["accounts/fireworks/models/qwen2p5-coder-3b-instruct","alibaba-qwen2-5-coder-3b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-3b-instruct","nscale/Qwen/Qwen2.5-Coder-3B-Instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-11-22 08:02:29"}],"meta":{"updated_at":"","request_id":"48d0fa33-9c6c-4e35-8b5f-15ca6b3af392","execution_ms":10}}