{"data":[{"id":"openai-gpt-oss-120b","name":"gpt-oss-120b","display_name":"GPT OSS 120B","description":"A 120-billion-parameter open-weights GPT model from OpenAI designed for reasoning-intensive tasks with implicit caching support.","creator":"openai","family":"gpt_oss","tier":"","version":null,"type":"language","size_in_bn":120,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":131072,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-06","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"GPT","capabilities":{"function_calling":true,"parallel_function_calling":true,"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":true,"adaptive_reasoning":false},"release_date":"2025-08-05","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":23,"ids":["@cf/openai/gpt-oss-120b","accounts/fireworks/models/gpt-oss-120b","azure_ai/gpt-oss-120b","baseten/openai/gpt-oss-120b","bedrock_mantle/openai.gpt-oss-120b","bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b","bedrock_mantle/us-gov-west-1/openai.gpt-oss-120b","bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0","bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0","cerebras/gpt-oss-120b","cloudflare/@cf/openai/gpt-oss-120b","crusoe/openai/gpt-oss-120b","databricks/databricks-gpt-oss-120b","deepinfra/openai/gpt-oss-120b","fireworks_ai/accounts/fireworks/models/gpt-oss-120b","fireworks_ai/gpt-oss-120b","gpt-oss-120b","gpt-oss-120b-low","gpt-oss-120b-maas","groq/openai/gpt-oss-120b","lemonade/gpt-oss-120b-mxfp-GGUF","nebius/openai/gpt-oss-120b","novita/openai/gpt-oss-120b","ollama/gpt-oss:120b-cloud","openai-gpt-oss-120b","openai-reasoning-gpt-oss-120b","openai.gpt-oss-120b-1:0","openai/gpt-oss-120b","openai/gpt-oss-120b:free","openrouter/openai/gpt-oss-120b","ovhcloud/gpt-oss-120b","publishers/google/models/gpt-oss-120b-maas","replicate/openai/gpt-oss-120b","sambanova/gpt-oss-120b","scaleway/openai/gpt-oss-120b","tensormesh/openai/gpt-oss-120b","together_ai/openai/gpt-oss-120b","vertex_ai/openai/gpt-oss-120b-maas","wandb/openai/gpt-oss-120b","watsonx/openai/gpt-oss-120b"],"hf_likes":4719,"hf_downloads":3524674,"hf_downloads_all_time":32348365,"hf_trending_score":25,"updated_at":"2026-09-21 08:02:25"},{"id":"alibaba-qwen2-5-72b-instruct","name":"qwen2-5-72b-instruct","display_name":"Qwen2.5 72B Instruct","description":"A 72-billion-parameter instruction-tuned LLM from Alibaba's Qwen2.5 series, excelling at natural language understanding, summarization, and dialogue.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":72,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"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":"2024-09-19","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["accounts/fireworks/models/qwen2p5-72b-instruct","alibaba-qwen2-5-72b-instruct","deepinfra/Qwen/Qwen2.5-72B-Instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-72b-instruct","huggingface-llm-qwen2-5-72b-instruct","hyperbolic/Qwen/Qwen2.5-72B-Instruct","nebius/Qwen/Qwen2.5-72B-Instruct","novita/qwen/qwen-2.5-72b-instruct","openrouter/qwen/qwen-2.5-72b-instruct","qwen/qwen-2.5-72b-instruct","Qwen/Qwen2.5-72B-Instruct","qwen2-5-72b-instruct","qwen2.5-72b-instruct","together_ai/Qwen/Qwen2.5-72B-Instruct"],"hf_likes":927,"hf_downloads":457915,"hf_downloads_all_time":5817981,"hf_trending_score":1,"updated_at":"2026-09-21 08:02:25"},{"id":"zhipu-glm-4-5-air","name":"glm-4-5-air","display_name":"GLM-4.5 Air","description":"A compact MoE variant of GLM-4.5 from Z AI, offering a lighter architecture while retaining strong agentic reasoning and tool-use performance.","creator":"zhipu","family":"glm4_moe","tier":"air","version":"4-5","type":"language","size_in_bn":110.469,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":98304,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-12-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":true,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-07-25","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":7,"ids":["accounts/fireworks/models/glm-4p5-air","fireworks_ai/accounts/fireworks/models/glm-4p5-air","glm-4-5-air","novita/zai-org/glm-4.5-air","openrouter/z-ai/glm-4.5-air","pinstripes/ps/glm-4.5-air","vercel_ai_gateway/zai/glm-4.5-air","z-ai/glm-4.5-air","z-ai/glm-4.5-air:free","zai-org/glm-4.5-air","zai/glm-4.5-air","zhipu-glm-4-5-air"],"hf_likes":599,"hf_downloads":389697,"hf_downloads_all_time":3025118,"hf_trending_score":2,"updated_at":"2026-09-21 08:02:25"},{"id":"alibaba-qwen3-14b","name":"qwen3-14b","display_name":"Qwen3 14B","description":"A 14-billion-parameter LLM from Alibaba's Qwen3 series with strong reasoning and tool-use capabilities for complex instruction-following tasks.","creator":"alibaba","family":"qwen3","tier":"","version":null,"type":"language","size_in_bn":14,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"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":true,"adaptive_reasoning":false},"release_date":"2025-04-28","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/qwen3-14b","alibaba-qwen3-14b","alibaba/qwen-3-14b","deepinfra/Qwen/Qwen3-14B","fireworks_ai/accounts/fireworks/models/qwen3-14b","huggingface-reasoning-qwen3-14b","nebius/Qwen/Qwen3-14B","openrouter/qwen/qwen3-14b","qwen/qwen3-14b","Qwen/Qwen3-14B","qwen3-14b","qwen3-14b-instruct","qwen3-14b-instruct-reasoning","vercel_ai_gateway/alibaba/qwen-3-14b"],"hf_likes":386,"hf_downloads":3005499,"hf_downloads_all_time":14478982,"hf_trending_score":3,"updated_at":"2026-09-21 08:02:25"},{"id":"alibaba-qwen3-8b","name":"qwen3-8b","display_name":"Qwen3 8B","description":"An 8B-parameter dense LLM from the Qwen3 series with strong reasoning capabilities and support for hybrid thinking and non-thinking inference modes.","creator":"alibaba","family":"qwen3","tier":"","version":null,"type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":20000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2025-03-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen3","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"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":true,"adaptive_reasoning":false},"release_date":"2025-04-28","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/qwen3-8b","alibaba-qwen3-8b","fireworks_ai/accounts/fireworks/models/qwen3-8b","huggingface-reasoning-qwen3-8b","llamagate/qwen3-8b","novita/qwen/qwen3-8b-fp8","openrouter/qwen/qwen3-8b","qwen/qwen3-8b","qwen/qwen3-8b-fp8","qwen3-8b","qwen3-8b-instruct","qwen3-8b-instruct-reasoning"],"hf_likes":1051,"hf_downloads":8692944,"hf_downloads_all_time":50107992,"hf_trending_score":9,"updated_at":"2026-09-21 08:02:25"},{"id":"deepseek-r1-distill-qwen-32b","name":"deepseek-r1-distill-qwen-32b","display_name":"DeepSeek R1 Distill Qwen 32B","description":"A 32B Qwen-based model distilled from DeepSeek R1's reasoning capabilities, offering high-quality chain-of-thought performance at a mid-scale parameter count.","creator":"deepseek","family":"deepseek-r1","tier":"","version":"1.0","type":"language","size_in_bn":32,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":32000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-07-31","training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Qwen","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"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":true,"adaptive_reasoning":false},"release_date":"2025-01-29","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","accounts/fireworks/models/deepseek-r1-distill-qwen-32b","cloudflare/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B","deepseek-llm-r1-distill-qwen-32b","deepseek-r1-distill-qwen-32b","deepseek/deepseek-r1-distill-qwen-32b","fireworks_ai/accounts/fireworks/models/deepseek-r1-distill-qwen-32b","novita/deepseek/deepseek-r1-distill-qwen-32b","nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"],"hf_likes":1545,"hf_downloads":1046750,"hf_downloads_all_time":23929632,"hf_trending_score":3,"updated_at":"2026-09-21 08:02:25"},{"id":"google-gemma-3-12b-instruct","name":"gemma-3-12b-instruct","display_name":"Gemma 3 12B Instruct","description":"An instruction-tuned 12B Gemma 3 LLM supporting vision-language inputs and 128k context.","creator":"google","family":"gemma3_text","tier":"","version":"3","type":"language","size_in_bn":12,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-08-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Gemini","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":"2025-03-13","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["@cf/google/gemma-3-12b-it","accounts/fireworks/models/gemma-3-12b-it","crusoe/google/gemma-3-12b-it","deepinfra/google/gemma-3-12b-it","google-gemma-3-12b-instruct","google.gemma-3-12b-it","google/gemma-3-12b-it","google/gemma-3-12b-it:free","novita/google/gemma-3-12b-it","openrouter/google/gemma-3-12b-it"],"hf_likes":707,"hf_downloads":2516014,"hf_downloads_all_time":14080610,"hf_trending_score":2,"updated_at":"2026-09-21 08:02:25"},{"id":"meta-muse-glimmer-30b","name":"muse-glimmer-30b","display_name":"Muse Glimmer 30B","description":"A 30B dense open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware.","creator":"meta","family":"muse","tier":"","version":null,"type":"language","size_in_bn":30,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":117964,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"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":true,"adaptive_reasoning":false},"release_date":"2026-08-09","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":6,"ids":["accounts/fireworks/models/muse-glimmer-30b","deepinfra/meta-models/Muse-Glimmer-30B","fireworks_ai/accounts/fireworks/models/muse-glimmer-30b","huggingface-vlm-muse-glimmer-30b","meta-models/Muse-Glimmer-30B","meta-muse-glimmer-30b","meta/muse-glimmer-30b","openrouter/meta/muse-glimmer-30b","openrouter/meta/muse-glimmer-30b:batch","together_ai/meta-models/Muse-Glimmer-30B"],"hf_likes":1146,"hf_downloads":0,"hf_downloads_all_time":0,"hf_trending_score":1099,"updated_at":"2026-09-21 08:02:25"},{"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":6,"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":"2026-09-21 08:02:25"},{"id":"openai-gpt-4o-mini","name":"gpt-4o-mini","display_name":"GPT-4o mini","description":"A fast, cost-efficient small LLM in the GPT-4o family that accepts text and image inputs, ideal for focused tasks and fine-tuning.","creator":"openai","family":"gpt","tier":"mini","version":"4o","type":"language","size_in_bn":null,"modalities":{"input":["image","pdf","text"],"output":["text"]},"context_window":131072,"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":true,"reasoning":false,"web_search":true,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2024-07-18","earliest_deprecation_date":"2027-04-14","deprecated":false,"has_pricing":true,"provider_count":6,"ids":["azure/eu/gpt-4o-mini-2024-07-18","azure/global-standard/gpt-4o-mini","azure/gpt-4o-mini","azure/gpt-4o-mini-2024-07-18","azure/us/gpt-4o-mini-2024-07-18","ft:gpt-4o-mini-2024-07-18","github_copilot/gpt-4o-mini","github_copilot/gpt-4o-mini-2024-07-18","gmi/openai/gpt-4o-mini","gpt-4o-mini","gpt-4o-mini-2024-07-18","gpt-4o-mini-realtime-dec-2024","gradient_ai/openai-gpt-4o-mini","openai-gpt-4o-mini","openai/gpt-4o-mini","openai/gpt-4o-mini-2024-07-18","openai/gpt-4o-mini:batch","openrouter/openai/gpt-4o-mini","openrouter/openai/gpt-4o-mini-2024-07-18","replicate/openai/gpt-4o-mini","vercel_ai_gateway/openai/gpt-4o-mini"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-09-21 08:02:25"}],"meta":{"updated_at":"","request_id":"3e646a32-c7b3-4148-a67c-2e9b028f29cc","execution_ms":8}}