{"data":[{"id":"meta-llama-3-8b-instruct","name":"llama-3-8b-instruct","display_name":"Llama 3 8B Instruct","description":"Meta's 8B instruction-tuned LLM from the Llama 3 generation, offering fast and cost-effective instruction-following across diverse tasks.","creator":"meta","family":"llama","tier":"","version":"3","type":"language","size_in_bn":8,"modalities":{"input":["pdf","text"],"output":["text"]},"context_window":32000,"max_output_tokens":8192,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-12-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Llama3","capabilities":{"function_calling":true,"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":true,"adaptive_reasoning":false},"release_date":"2024-04-23","earliest_deprecation_date":"2026-06-19","deprecated":false,"has_pricing":true,"provider_count":8,"ids":["@cf/meta/llama-3-8b-instruct","accounts/fireworks/models/llama-v3-8b-instruct","accounts/fireworks/models/llama-v3-8b-instruct-hf","accounts/fireworks/models/llama-v3-8b-instruct-v0","anyscale/meta-llama/Meta-Llama-3-8B-Instruct","bedrock/ap-south-1/meta.llama3-8b-instruct-v1:0","bedrock/ca-central-1/meta.llama3-8b-instruct-v1:0","bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0","bedrock/eu-west-2/meta.llama3-8b-instruct-v1:0","bedrock/sa-east-1/meta.llama3-8b-instruct-v1:0","bedrock/us-east-1/meta.llama3-8b-instruct-v1:0","bedrock/us-gov-east-1/meta.llama3-8b-instruct-v1:0","bedrock/us-gov-west-1/meta.llama3-8b-instruct-v1:0","bedrock/us-west-1/meta.llama3-8b-instruct-v1:0","deepinfra/meta-llama/Meta-Llama-3-8B-Instruct","fireworks_ai/accounts/fireworks/models/llama-v3-8b-instruct-hf","gradient_ai/llama3-8b-instruct","huggingface-llm-gradientai-llama-3-8B-instruct-262k","huggingface-llm-llama-3-8b-instruct-gradient","llama-3-instruct-8b","meta-llama-3-8b-instruct","meta-llama/llama-3-8b-instruct","meta-llama/Meta-Llama-3-8B-Instruct","meta-textgeneration-llama-3-8b-instruct","meta-textgenerationneuron-llama-3-8b-instruct","meta.llama3-8b-instruct-v1:0","novita/meta-llama/llama-3-8b-instruct","replicate/meta/llama-3-8b-instruct","vertex_ai/meta/llama3-8b-instruct-maas"],"hf_likes":4486,"hf_downloads":1342402,"hf_downloads_all_time":40122839,"hf_trending_score":1.5,"updated_at":"2026-08-12 08:02:44"},{"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","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":"2026-08-12 08:02:44"},{"id":"gryphe-mythomax-l2-13b","name":"mythomax-l2-13b","display_name":"MythoMax L2 13B","description":"A 13B Llama 2-based LLM fine-tuned via experimental tensor-merge techniques for strong performance in both creative storytelling and roleplay scenarios.","creator":"gryphe","family":"llama","tier":"","version":null,"type":"language","size_in_bn":13,"modalities":{"input":["text"],"output":["text"]},"context_window":8192,"max_output_tokens":4096,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-06-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Llama2","capabilities":{"function_calling":true,"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":true,"adaptive_reasoning":false},"release_date":"2023-07-02","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["accounts/fireworks/models/mythomax-l2-13b","deepinfra/Gryphe/MythoMax-L2-13b","fireworks_ai/accounts/fireworks/models/mythomax-l2-13b","gryphe-mythomax-l2-13b","gryphe/mythomax-l2-13b","Gryphe/MythoMax-L2-13b","novita/gryphe/mythomax-l2-13b","openrouter/gryphe/mythomax-l2-13b"],"hf_likes":377,"hf_downloads":1784,"hf_downloads_all_time":728893,"hf_trending_score":0,"updated_at":"2026-08-12 08:02:44"},{"id":"meta-llama-3-8b","name":"meta-llama-3-8b","display_name":"Llama 3 8B","description":"Meta's compact 8B pre-trained LLM from the Llama 3 generation, suitable for efficient on-device and low-cost cloud inference.","creator":"meta","family":"llama","tier":"","version":"3","type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":8192,"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":4,"ids":["accounts/fireworks/models/llama-v3-8b","fireworks_ai/accounts/fireworks/models/llama-v3-8b","meta-llama-3-8b","meta-textgeneration-llama-3-8b","meta-textgenerationneuron-llama-3-8b","ollama/llama3:8b","replicate/meta/llama-3-8b","snowflake/llama3-8b","vercel_ai_gateway/meta/llama-3-8b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"openai-gpt-3-5-turbo-instruct","name":"gpt-3-5-turbo-instruct","display_name":"GPT-3.5 Turbo Instruct","description":"A GPT-3.5 Turbo variant tuned for instruction-following in completion mode, omitting chat-specific optimizations for direct prompt-response use.","creator":"openai","family":"gpt","tier":"","version":"3-5","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":8192,"max_output_tokens":4097,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2021-09-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"GPT","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":true,"adaptive_reasoning":false},"release_date":"2023-09-28","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["azure/gpt-3.5-turbo-instruct-0914","azure/gpt-35-turbo-instruct","azure/gpt-35-turbo-instruct-0914","gpt-3.5-turbo-instruct","gpt-3.5-turbo-instruct-0914","openai-gpt-3-5-turbo-instruct","openai/gpt-3.5-turbo-instruct","vercel_ai_gateway/openai/gpt-3.5-turbo-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"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":"2026-08-12 08:02:44"},{"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":"2026-08-12 08:02:44"},{"id":"google-gemma-7b-instruct","name":"gemma-7b-instruct","display_name":"Gemma 7B IT","description":"Instruction-tuned 7B Gemma model fine-tuned for following natural language instructions in conversational and task-oriented settings.","creator":"google","family":"gemma","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":8192,"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":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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/gemma-7b-it","anyscale/google/gemma-7b-it","fireworks_ai/accounts/fireworks/models/gemma-7b-it","google-gemma-7b-instruct","groq/gemma-7b-it","huggingface-llm-gemma-7b-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"meta-codellama-34b-instruct","name":"meta-codellama-34b-instruct","display_name":"Code Llama 34B Instruct","description":"A 34B-parameter instruction-tuned Code Llama model designed to follow natural language instructions for code generation tasks.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":34,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"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":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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["accounts/fireworks/models/code-llama-34b-instruct","anyscale/codellama/CodeLlama-34b-Instruct-hf","fireworks_ai/accounts/fireworks/models/code-llama-34b-instruct","meta-codellama-34b-instruct","meta-textgeneration-llama-codellama-34b-instruct","perplexity/codellama-34b-instruct","together_ai/togethercomputer/CodeLlama-34b-Instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"meta-codellama-70b-instruct","name":"meta-codellama-70b-instruct","display_name":"Code Llama 70B Instruct","description":"A 70B-parameter instruction-tuned Code Llama model designed to follow natural language instructions for complex code generation tasks.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"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":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/code-llama-70b-instruct","anyscale/codellama/CodeLlama-70b-Instruct-hf","fireworks_ai/accounts/fireworks/models/code-llama-70b-instruct","meta-codellama-70b-instruct","meta-textgeneration-llama-codellama-70b-instruct","perplexity/codellama-70b-instruct"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"}],"meta":{"updated_at":"","request_id":"1f24e477-a144-4859-aeeb-dd2ef704ae99","execution_ms":2}}