{"data":[{"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":"2026-06-19 08:02:10"},{"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":"2026-06-19 08:02:10"},{"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":"2026-06-19 08:02:10"},{"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":"2026-06-19 08:02:10"},{"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":"2026-06-19 08:02:10"},{"id":"meta-llama-3-70b","name":"meta-llama-3-70b","display_name":"Llama 3 70B","description":"Meta's 70B pre-trained LLM from the Llama 3 generation, offering strong general-purpose text generation and reasoning capabilities.","creator":"meta","family":"llama","tier":"","version":"3","type":"language","size_in_bn":70,"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":3,"ids":["meta-llama-3-70b","meta-textgeneration-llama-3-70b","meta-textgenerationneuron-llama-3-70b","ollama/llama3:70b","replicate/meta/llama-3-70b","snowflake/llama3-70b","vercel_ai_gateway/meta/llama-3-70b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-19 08:02:10"},{"id":"microsoft-phi-4","name":"phi-4","display_name":"Phi-4","description":"A small language model from Microsoft trained on high-quality synthetic and curated datasets, excelling at reasoning and STEM tasks despite its compact size.","creator":"microsoft","family":"phi","tier":"","version":"4","type":"language","size_in_bn":14.66,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"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":"Other","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":"2025-01-10","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["azure_ai/Phi-4","deepinfra/microsoft/phi-4","microsoft-phi-4","microsoft/phi-4","phi-4","phi-4-mini","phi-4-multimodal","publishers/microsoft/models/phi4"],"hf_likes":2248,"hf_downloads":874552,"hf_downloads_all_time":11669853,"hf_trending_score":4,"updated_at":"2026-06-19 08:02:10"},{"id":"openai-gpt-3-5-turbo-16k","name":"gpt-3-5-turbo-16k","display_name":"GPT-3.5 Turbo 16k","description":"An extended-context variant of GPT-3.5 Turbo supporting up to 16,384 tokens, suitable for longer documents and multi-turn conversations.","creator":"openai","family":"gpt","tier":"","version":"3-5","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":16385,"max_output_tokens":4096,"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":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":"2023-08-28","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["azure/gpt-35-turbo-16k","azure/gpt-35-turbo-16k-0613","gpt-3.5-turbo-16k","openai-gpt-3-5-turbo-16k","openai/gpt-3.5-turbo-16k","openrouter/openai/gpt-3.5-turbo-16k"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-19 08:02:10"},{"id":"sao10k-l3-lunaris-8b","name":"l3-lunaris-8b","display_name":"L3 Lunaris 8B","description":"An 8B Llama 3-based generalist and roleplay model merge from Sao10k, balancing broad instruction-following with creative narrative capability.","creator":"sao10k","family":"llama","tier":"","version":null,"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":"2023-12-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Llama3","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":"2024-08-13","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["novita/sao10k/l3-8b-lunaris","sao10k-l3-lunaris-8b","sao10k/l3-8b-lunaris","sao10k/l3-lunaris-8b"],"hf_likes":142,"hf_downloads":1932,"hf_downloads_all_time":450639,"hf_trending_score":0,"updated_at":"2026-06-19 08:02:10"},{"id":"ai21-j2-mid","name":"ai21-j2-mid","display_name":"Jurassic-2 Mid","description":"A mid-tier Jurassic-2 LLM balancing quality and cost for a wide range of text generation and completion tasks.","creator":"ai21","family":"jurassic","tier":"mid","version":null,"type":"language","size_in_bn":null,"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":2,"ids":["ai21-j2-mid","ai21.j2-mid-v1","j2-mid"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-19 08:02:10"}],"meta":{"updated_at":"","request_id":"142bd85b-bf14-4948-9470-467e5597a258","execution_ms":9}}