{"data":[{"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":"2026-10-17 08:02:51"},{"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":4,"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":"2026-10-17 08:02:51"},{"id":"amazon-nova-micro","name":"nova-micro","display_name":"Nova Micro","description":"Amazon's smallest and fastest Nova model, optimized for text-only tasks requiring ultra-low latency.","creator":"amazon","family":"nova","tier":"micro","version":null,"type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"max_output_tokens":10000,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2024-10-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Nova","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":false,"adaptive_reasoning":false},"release_date":"2024-12-03","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["amazon-nova-micro","amazon-nova/nova-micro-v1","amazon.nova-micro-v1:0","amazon.nova-micro-v1:0:128k","amazon.nova-micro-v1:0:24k","amazon/nova-micro","amazon/nova-micro-v1","apac.amazon.nova-micro-v1:0","bedrock/us-gov-west-1/amazon.nova-micro-v1:0","eu.amazon.nova-micro-v1:0","nova-micro","nova-textgeneration-micro","openrouter/amazon/nova-micro-v1","us.amazon.nova-micro-v1:0","vercel_ai_gateway/amazon/nova-micro"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-17 08:02:51"},{"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":4,"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":"2026-10-17 08:02:51"},{"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":3,"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":"2026-10-17 08:02:51"},{"id":"alibaba-qwen2-5-coder-7b-instruct","name":"qwen2-5-coder-7b-instruct","display_name":"Qwen2.5 Coder 7B Instruct","description":"A 7-billion-parameter instruction-tuned code LLM from Alibaba's Qwen2.5-Coder series, designed for responsive code generation and developer assistance.","creator":"alibaba","family":"qwen2","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"max_output_tokens":8192,"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":3,"ids":["accounts/fireworks/models/qwen2p5-coder-7b-instruct","alibaba-qwen2-5-coder-7b-instruct","fireworks_ai/accounts/fireworks/models/qwen2p5-coder-7b-instruct","huggingface-llm-qwen2-5-coder-7b-instruct","nscale/Qwen/Qwen2.5-Coder-7B-Instruct","qwen2-5-coder-7b-instruct","qwen2.5-coder-7b-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-17 08:02:51"},{"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":"2026-10-17 08:02:51"},{"id":"deepseek-r1-turbo","name":"deepseek-r1-turbo","display_name":"DeepSeek R1 Turbo","description":"A turbo-speed variant of DeepSeek R1 optimized for faster inference while preserving the model's strong mathematical and logical reasoning abilities.","creator":"deepseek","family":"deepseek-r1","tier":"turbo","version":"1.0","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":64000,"max_output_tokens":16000,"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":true,"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":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["deepinfra/deepseek-ai/DeepSeek-R1-Turbo","deepseek-r1-turbo","deepseek/deepseek-r1-turbo","novita/deepseek/deepseek-r1-turbo"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-17 08:02:51"},{"id":"inception-mercury-2","name":"mercury-2","display_name":"Mercury 2","description":"A fast reasoning diffusion LLM from Inception Labs that produces and refines multiple tokens in parallel, combining reasoning capability with diffusion-based speed.","creator":"inception","family":"mercury","tier":"","version":"2","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"max_output_tokens":50000,"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":"2026-03-04","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["inception-mercury-2","inception/mercury-2","mercury-2","openrouter/inception/mercury-2"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-17 08:02:51"},{"id":"meta-llama-3-1-70b","name":"meta-llama-3-1-70b","display_name":"Llama 3.1 70B","description":"Meta's 70B pre-trained LLM in the Llama 3.1 series, balancing high capability with practical deployment costs and supporting tool-use tasks.","creator":"meta","family":"llama","tier":"","version":"3-1","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"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":"2024-07-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["cerebras/llama3.1-70b","meta-llama-3-1-70b","meta-textgeneration-llama-3-1-70b","meta-textgenerationneuron-llama-3-1-70b","meta/llama-3.1-70b","snowflake/llama3.1-70b","vercel_ai_gateway/meta/llama-3.1-70b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-10-17 08:02:51"}],"meta":{"updated_at":"","request_id":"3732748b-be28-4695-a322-9d880215a95c","execution_ms":10}}