{"data":[{"id":"nvidia-llama-nemotron-1-5-super-49b-reasoning","name":"llama-nemotron-1-5-super-49b-reasoning","display_name":"Llama Nemotron 1.5 Super 49B Reasoning","description":"A reasoning-focused 49B-parameter variant of NVIDIA's Llama Nemotron 1.5 Super, designed for extended chain-of-thought and multi-step inference.","creator":"nvidia","family":"llama","tier":"super","version":"1-5","type":"","size_in_bn":null,"modalities":{"input":[],"output":[]},"context_window":null,"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":false,"provider_count":0,"ids":["llama-nemotron-super-49b-v1-5-reasoning","nvidia-llama-nemotron-1-5-super-49b-reasoning"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-04-20 16:51:01"},{"id":"nvidia-llama-3-3-nemotron-super-49b-reasoning","name":"llama-3-3-nemotron-super-49b-reasoning","display_name":"Llama 3.3 Nemotron Super 49B Reasoning","description":"A reasoning-specialized 49B-parameter variant of NVIDIA's Nemotron Super built on Llama 3.3, optimized for complex multi-step problem solving.","creator":"nvidia","family":"llama","tier":"super","version":null,"type":"","size_in_bn":null,"modalities":{"input":[],"output":[]},"context_window":null,"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":false,"provider_count":0,"ids":["llama-3-3-nemotron-super-49b-reasoning","nvidia-llama-3-3-nemotron-super-49b-reasoning"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-04-20 16:51:01"},{"id":"nousresearch-hermes-4-llama-3-1-70b-reasoning","name":"hermes-4-llama-3-1-70b-reasoning","display_name":"Hermes 4 Llama 3.1 70B Reasoning","description":"The reasoning-mode variant of Nous Research's 70B Hermes 4 Llama 3.1 model, optimized for extended chain-of-thought problem solving.","creator":"nousresearch","family":"llama","tier":"","version":null,"type":"","size_in_bn":null,"modalities":{"input":[],"output":[]},"context_window":null,"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":false,"provider_count":0,"ids":["hermes-4-llama-3-1-70b-reasoning","nousresearch-hermes-4-llama-3-1-70b-reasoning"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-04-20 16:51:01"},{"id":"nvidia-llama-3-1-nemotron-1-ultra-253b-reasoning","name":"llama-3-1-nemotron-1-ultra-253b-reasoning","display_name":"Llama 3.1 Nemotron 1 Ultra 253B Reasoning","description":"A 253B-parameter reasoning-specialized variant of NVIDIA's Nemotron Ultra, built on Llama 3.1 for complex multi-step inference and agentic workflows.","creator":"nvidia","family":"llama","tier":"ultra","version":"1","type":"","size_in_bn":null,"modalities":{"input":[],"output":[]},"context_window":null,"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":false,"provider_count":0,"ids":["llama-3-1-nemotron-ultra-253b-v1-reasoning","nvidia-llama-3-1-nemotron-1-ultra-253b-reasoning"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-04-20 16:51:01"},{"id":"nousresearch-hermes-4-llama-3-1-405b-reasoning","name":"hermes-4-llama-3-1-405b-reasoning","display_name":"Hermes 4 Llama 3.1 405B Reasoning","description":"The reasoning-mode variant of Nous Research's 405B Hermes 4 Llama 3.1 model, configured for extended chain-of-thought deliberation.","creator":"nousresearch","family":"llama","tier":"","version":null,"type":"","size_in_bn":null,"modalities":{"input":[],"output":[]},"context_window":null,"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":false,"provider_count":0,"ids":["hermes-4-llama-3-1-405b-reasoning","nousresearch-hermes-4-llama-3-1-405b-reasoning"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-04-20 16:51:01"},{"id":"nousresearch-hermes-4-llama-3-1-405b","name":"hermes-4-llama-3-1-405b","display_name":"Hermes 4 Llama 3.1 405B","description":"A 405B-parameter Llama 3.1-based hybrid reasoning LLM from Nous Research with selectable deliberate thinking or direct response modes.","creator":"nousresearch","family":"llama","tier":"","version":null,"type":"language","size_in_bn":405,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["hermes-4-llama-3-1-405b","hermes-4-llama-3-1-405b-reasoning","nousresearch-hermes-4-llama-3-1-405b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"nvidia-llama-nemotron-1-5-super-49b","name":"llama-nemotron-1-5-super-49b","display_name":"Llama Nemotron 1.5 Super 49B","description":"A 49B-parameter Nemotron Super model at version 1.5, fine-tuned by NVIDIA on a Llama base for efficient reasoning and agentic task performance.","creator":"nvidia","family":"llama","tier":"super","version":"1-5","type":"language","size_in_bn":49,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["llama-nemotron-super-49b-v1-5","llama-nemotron-super-49b-v1-5-reasoning","nvidia-llama-nemotron-1-5-super-49b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"nvidia-llama-3-1-nemotron-nano-4b-reasoning","name":"llama-3-1-nemotron-nano-4b-reasoning","display_name":"Llama 3.1 Nemotron Nano 4B Reasoning","description":"A compact 4B-parameter reasoning model from NVIDIA's Nemotron Nano series, derived from Llama 3.1 for efficient on-device inference with reasoning capabilities.","creator":"nvidia","family":"llama","tier":"nano","version":null,"type":"language","size_in_bn":4,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["llama-3-1-nemotron-nano-4b-reasoning","nvidia-llama-3-1-nemotron-nano-4b-reasoning"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"nvidia-llama-3-3-nemotron-super-49b","name":"llama-3-3-nemotron-super-49b","display_name":"Llama 3.3 Nemotron Super 49B","description":"A 49B-parameter compute-efficient LLM fine-tuned by NVIDIA on Llama 3.3, targeting multi-agent and agentic system workloads with the Nemotron Super architecture.","creator":"nvidia","family":"llama","tier":"super","version":null,"type":"language","size_in_bn":49,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["llama-3-3-nemotron-super-49b","llama-3-3-nemotron-super-49b-reasoning","nvidia-llama-3-3-nemotron-super-49b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"allenai-tulu-3-405b","name":"tulu-3-405b","display_name":"Llama 3.1 Tulu3 405B","description":"A 405B instruction-tuned LLM from the Allen Institute for AI built on Llama 3.1, applying the Tulu 3 post-training recipe for strong alignment and instruction-following.","creator":"allenai","family":"llama","tier":"","version":"3","type":"language","size_in_bn":405,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["allenai-tulu-3-405b","tulu3-405b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"nousresearch-hermes-4-llama-3-1-70b","name":"hermes-4-llama-3-1-70b","display_name":"Hermes 4 Llama 3.1 70B","description":"A 70B-parameter Llama 3.1-based hybrid reasoning LLM from Nous Research supporting both deliberate thinking and direct instruction-following.","creator":"nousresearch","family":"llama","tier":"","version":null,"type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["hermes-4-llama-3-1-70b","hermes-4-llama-3-1-70b-reasoning","nousresearch-hermes-4-llama-3-1-70b"],"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-llama-3-1-70b-instruct","name":"llama-3-1-70b-instruct","display_name":"Llama 3.1 70B Instruct","description":"Meta's 70B instruction-tuned LLM with strong tool-use and multilingual capabilities, widely deployed across cloud regions for enterprise workloads.","creator":"meta","family":"llama","tier":"","version":"3-1","type":"language","size_in_bn":70,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"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":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":"2024-07-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":12,"ids":["accounts/fireworks/models/llama-v3p1-70b-instruct","accounts/fireworks/models/llama-v3p1-70b-instruct-1b","azure_ai/Meta-Llama-3.1-70B-Instruct","deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct","deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct","fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b","friendliai/meta-llama-3.1-70b-instruct","hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct","lambda_ai/llama3.1-70b-instruct-fp8","llama-3-1-instruct-70b","meta-llama-3-1-70b-instruct","meta-llama/llama-3.1-70b-instruct","meta-llama/Meta-Llama-3.1-70B-Instruct","meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","meta-textgeneration-llama-3-1-70b-instruct","meta-textgenerationneuron-llama-3-1-70b-instruct","meta.llama3-1-70b-instruct-v1:0","meta.llama3-1-70b-instruct-v1:0:128k","nebius/meta-llama/Meta-Llama-3.1-70B-Instruct","oci/meta.llama-3.1-70b-instruct","ovhcloud/Meta-Llama-3_1-70B-Instruct","perplexity/llama-3.1-70b-instruct","together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","us.meta.llama3-1-70b-instruct-v1:0","vertex_ai/meta/llama-3.1-70b-instruct-maas"],"hf_likes":907,"hf_downloads":737459,"hf_downloads_all_time":20735812,"hf_trending_score":0,"updated_at":"2026-08-12 08:02:44"},{"id":"meta-llama-3-2-90b-instruct-vision","name":"llama-3-2-90b-instruct-vision","display_name":"Llama 3.2 90B Instruct Vision","description":"Meta's 90B instruction-tuned vision-language model from Llama 3.2, combining large-scale multimodal understanding with instruction-following capabilities.","creator":"meta","family":"llama","tier":"","version":"3-2","type":"","size_in_bn":null,"modalities":{"input":[],"output":[]},"context_window":null,"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":false,"provider_count":0,"ids":["llama-3-2-instruct-90b-vision","meta-llama-3-2-90b-instruct-vision"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-04-20 16:51:01"},{"id":"nousresearch-hermes-3-llama-3-1-70b","name":"hermes-3-llama-3-1-70b","display_name":"Hermes 3 Llama 3.1 70B","description":"A 70B-parameter Llama 3.1-based LLM from Nous Research with Hermes 3 fine-tuning for improved agentic capabilities and long-context coherence.","creator":"nousresearch","family":"llama","tier":"","version":null,"type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":16384,"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":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":"2024-08-18","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["deepinfra/NousResearch/Hermes-3-Llama-3.1-70B","hermes-3-llama-3-1-70b","hyperbolic/NousResearch/Hermes-3-Llama-3.1-70B","nousresearch-hermes-3-llama-3-1-70b","nousresearch/hermes-3-llama-3.1-70b","NousResearch/Hermes-3-Llama-3.1-70B"],"hf_likes":123,"hf_downloads":2494,"hf_downloads_all_time":179146,"hf_trending_score":1,"updated_at":"2026-08-12 08:02:44"},{"id":"meta-llama-2-7b-chat","name":"llama-2-7b-chat","display_name":"Llama 2 7B Chat","description":"A 7B Llama 2 model fine-tuned with RLHF for dialogue use cases, offering an efficient and accessible conversational LLM.","creator":"meta","family":"llama","tier":"","version":"2","type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":4096,"max_output_tokens":4096,"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":["@cf/meta/llama-2-7b-chat-fp16","accounts/fireworks/models/llama-v2-7b-chat","anyscale/meta-llama/Llama-2-7b-chat-hf","cloudflare/@cf/meta/llama-2-7b-chat-fp16","cloudflare/@cf/meta/llama-2-7b-chat-int8","fireworks_ai/accounts/fireworks/models/llama-v2-7b-chat","llama-2-chat-7b","meta-llama-2-7b-chat","replicate/meta/llama-2-7b-chat"],"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-llama-3-2-11b-instruct-vision","name":"llama-3-2-11b-instruct-vision","display_name":"Llama 3.2 11B Instruct Vision","description":"Meta's 11B instruction-tuned vision-language model from Llama 3.2, combining image understanding with instruction-following for multimodal applications.","creator":"meta","family":"llama","tier":"","version":"3-2","type":"","size_in_bn":null,"modalities":{"input":[],"output":[]},"context_window":null,"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":false,"provider_count":0,"ids":["llama-3-2-instruct-11b-vision","meta-llama-3-2-11b-instruct-vision"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-04-20 16:51:01"},{"id":"meta-llama-2-13b-chat","name":"llama-2-13b-chat","display_name":"Llama 2 13B Chat","description":"A 13B Llama 2 model fine-tuned with RLHF for dialogue use cases, optimized for helpful and safe conversational interactions.","creator":"meta","family":"llama","tier":"","version":"2","type":"language","size_in_bn":13,"modalities":{"input":["text"],"output":["text"]},"context_window":4096,"max_output_tokens":4096,"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-v2-13b-chat","anyscale/meta-llama/Llama-2-13b-chat-hf","fireworks_ai/accounts/fireworks/models/llama-v2-13b-chat","llama-2-chat-13b","meta-llama-2-13b-chat","meta.llama2-13b-chat-v1","replicate/meta/llama-2-13b-chat"],"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-llama-2-70b-chat","name":"llama-2-70b-chat","display_name":"Llama 2 70B Chat","description":"A 70B Llama 2 model fine-tuned with RLHF for dialogue, providing high-quality conversational responses at the largest Llama 2 scale.","creator":"meta","family":"llama","tier":"","version":"2","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":4096,"max_output_tokens":4096,"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":6,"ids":["anyscale/meta-llama/Llama-2-70b-chat-hf","databricks/databricks-llama-2-70b-chat","fireworks_ai/accounts/fireworks/models/llama-v2-70b-chat","llama-2-chat-70b","meta-llama-2-70b-chat","meta.llama2-70b-chat-v1","perplexity/llama-2-70b-chat","replicate/meta/llama-2-70b-chat","snowflake/llama2-70b-chat"],"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-llama-65b","name":"llama-65b","display_name":"Llama 65B","description":"A large 65B-parameter open-weight LLM from Meta's original Llama series, designed for general-purpose language understanding and generation.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":65,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["llama-65b","meta-llama-65b"],"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-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":"aion-labs-llama-3-1-rp-8b","name":"llama-3-1-rp-8b","display_name":"Aion Llama 3.1 RP 8B","description":"An 8-billion-parameter Llama 3.1-based roleplaying model from AionLabs, achieving top rankings on the RPBench-Auto character evaluation benchmark.","creator":"aion-labs","family":"llama","tier":"","version":null,"type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":32768,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-12-31","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Other","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":"2025-02-04","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["aion-labs-llama-3-1-rp-8b","aion-labs/aion-rp-llama-3.1-8b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"nousresearch-chronos-hermes-2-13b","name":"chronos-hermes-2-13b","display_name":"Chronos Hermes 2 13B","description":"A 13B-parameter merged LLM combining Chronos and Nous Hermes Llama 2, blending imaginative writing style with coherent instruction-following.","creator":"nousresearch","family":"llama","tier":"","version":"2","type":"language","size_in_bn":13,"modalities":{"input":["text"],"output":["text"]},"context_window":4096,"max_output_tokens":4096,"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":1,"ids":["accounts/fireworks/models/chronos-hermes-13b-v2","fireworks_ai/accounts/fireworks/models/chronos-hermes-13b-v2","nousresearch-chronos-hermes-2-13b"],"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-13b","name":"meta-codellama-13b","display_name":"Code Llama 13B","description":"A 13B-parameter Code Llama model fine-tuned for general code synthesis and understanding across multiple programming languages.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":13,"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":1,"ids":["accounts/fireworks/models/code-llama-13b","fireworks_ai/accounts/fireworks/models/code-llama-13b","meta-codellama-13b","meta-textgeneration-llama-codellama-13b"],"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-13b-instruct","name":"meta-codellama-13b-instruct","display_name":"Code Llama 13B Instruct","description":"A 13B-parameter instruction-tuned Code Llama model designed to follow natural language instructions for code generation and understanding.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":13,"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":1,"ids":["accounts/fireworks/models/code-llama-13b-instruct","fireworks_ai/accounts/fireworks/models/code-llama-13b-instruct","meta-codellama-13b-instruct","meta-textgeneration-llama-codellama-13b-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-13b-python","name":"meta-codellama-13b-python","display_name":"Code Llama 13B Python","description":"A 13B-parameter Code Llama model specialized for Python code synthesis, completion, and understanding.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":13,"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":1,"ids":["accounts/fireworks/models/code-llama-13b-python","fireworks_ai/accounts/fireworks/models/code-llama-13b-python","meta-codellama-13b-python","meta-textgeneration-llama-codellama-13b-python"],"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","name":"meta-codellama-34b","display_name":"Code Llama 34B","description":"A 34B-parameter Code Llama model offering strong general code synthesis and understanding across multiple programming languages.","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":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":1,"ids":["accounts/fireworks/models/code-llama-34b","fireworks_ai/accounts/fireworks/models/code-llama-34b","meta-codellama-34b","meta-textgeneration-llama-codellama-34b"],"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-34b-python","name":"meta-codellama-34b-python","display_name":"Code Llama 34B Python","description":"A 34B-parameter Code Llama model specialized for Python code synthesis and understanding with enhanced Python-specific capabilities.","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":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":1,"ids":["accounts/fireworks/models/code-llama-34b-python","fireworks_ai/accounts/fireworks/models/code-llama-34b-python","meta-codellama-34b-python","meta-textgeneration-llama-codellama-34b-python"],"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","name":"meta-codellama-70b","display_name":"Code Llama 70B","description":"A 70B-parameter Code Llama model delivering high-capability code synthesis and understanding across a wide range of programming languages.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":4096,"max_output_tokens":4096,"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":1,"ids":["accounts/fireworks/models/code-llama-70b","fireworks_ai/accounts/fireworks/models/code-llama-70b","meta-codellama-70b","meta-textgeneration-llama-codellama-70b","meta-textgenerationneuron-llama-codellama-70b"],"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"},{"id":"meta-codellama-70b-python","name":"meta-codellama-70b-python","display_name":"Code Llama 70B Python","description":"A 70B-parameter Code Llama model specialized for Python code synthesis and understanding, offering the highest capacity in the Python-focused Code Llama series.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":4096,"max_output_tokens":4096,"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":1,"ids":["accounts/fireworks/models/code-llama-70b-python","fireworks_ai/accounts/fireworks/models/code-llama-70b-python","meta-codellama-70b-python","meta-textgeneration-llama-codellama-70b-python"],"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-7b","name":"meta-codellama-7b","display_name":"Code Llama 7B","description":"A 7B parameter Code Llama model fine-tuned on code data for general code synthesis and understanding across multiple programming languages.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":7,"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":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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["accounts/fireworks/models/code-llama-7b","fireworks_ai/accounts/fireworks/models/code-llama-7b","llamagate/codellama-7b","meta-codellama-7b","meta-textgeneration-llama-codellama-7b","meta-textgenerationneuron-llama-codellama-7b","publishers/meta/models/codellama-7b-hf"],"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-7b-instruct","name":"meta-codellama-7b-instruct","display_name":"Code Llama 7B Instruct","description":"A 7B instruction-tuned Code Llama model that follows natural language instructions to generate and explain code across multiple programming languages.","creator":"meta","family":"llama","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":16384,"max_output_tokens":16384,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":"2023-06-30","training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":"Other","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":"2025-04-14","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["accounts/fireworks/models/code-llama-7b-instruct","alfredpros/codellama-7b-instruct-solidity","cloudflare/@hf/thebloke/codellama-7b-instruct-awq","fireworks_ai/accounts/fireworks/models/code-llama-7b-instruct","meta-codellama-7b-instruct","meta-textgeneration-llama-codellama-7b-instruct"],"hf_likes":17,"hf_downloads":45,"hf_downloads_all_time":17680,"hf_trending_score":0,"updated_at":"2026-08-12 08:02:44"},{"id":"deepcogito-cogito-1-3b-preview-llama","name":"cogito-1-3b-preview-llama","display_name":"Cogito V1 Preview Llama 3B","description":"A compact 3B-parameter hybrid reasoning LLM from Deep Cogito built on the Llama architecture, balancing efficiency with instruction-following capability.","creator":"deepcogito","family":"llama","tier":"","version":"1","type":"language","size_in_bn":3,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":1,"ids":["accounts/fireworks/models/cogito-v1-preview-llama-3b","deepcogito-cogito-1-3b-preview-llama","fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-3b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"deepcogito-cogito-1-70b-preview-llama","name":"cogito-1-70b-preview-llama","display_name":"Cogito V1 Preview Llama 70B","description":"A 70B-parameter hybrid reasoning LLM from Deep Cogito built on the Llama architecture, designed for complex multi-step reasoning and instruction-following.","creator":"deepcogito","family":"llama","tier":"","version":"1","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":1,"ids":["accounts/fireworks/models/cogito-v1-preview-llama-70b","deepcogito-cogito-1-70b-preview-llama","fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-70b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"deepcogito-cogito-1-8b-preview-llama","name":"cogito-1-8b-preview-llama","display_name":"Cogito V1 Preview Llama 8B","description":"An 8B-parameter hybrid reasoning LLM from Deep Cogito built on the Llama architecture, combining efficient inference with strong reasoning capabilities.","creator":"deepcogito","family":"llama","tier":"","version":"1","type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":1,"ids":["accounts/fireworks/models/cogito-v1-preview-llama-8b","deepcogito-cogito-1-8b-preview-llama","fireworks_ai/accounts/fireworks/models/cogito-v1-preview-llama-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":"sentientai-dobby-llama-3-1-mini-8b-unhinged-plus","name":"dobby-llama-3-1-mini-8b-unhinged-plus","display_name":"Dobby Llama 3.1 Mini 8B Unhinged Plus","description":"An uncensored 8B LLM fine-tuned on Llama 3.1 Mini by Sentient AI, designed for unrestricted conversational responses.","creator":"sentientai","family":"llama","tier":"mini","version":null,"type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":1,"ids":["fireworks_ai/accounts/fireworks/models/dobby-mini-unhinged-plus-llama-3-1-8b","sentientai-dobby-llama-3-1-mini-8b-unhinged-plus"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"sentientai-dobby-llama-3-3-70b-unhinged","name":"dobby-llama-3-3-70b-unhinged","display_name":"Dobby Llama 3.3 70B Unhinged","description":"A large 70B uncensored LLM fine-tuned on Llama 3.3 by Sentient AI, targeting uninhibited and open-ended dialogue.","creator":"sentientai","family":"llama","tier":"","version":null,"type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"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":1,"ids":["fireworks_ai/accounts/fireworks/models/dobby-unhinged-llama-3-3-70b-new","sentientai-dobby-llama-3-3-70b-unhinged"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"cognitive-computations-dolphin-llama3-2-9-8b","name":"dolphin-llama3-2-9-8b","display_name":"Dolphin 2.9 Llama 3 8B","description":"An uncensored 8B instruction-tuned LLM fine-tuned on Llama 3 with broad instruction-following, conversational, and coding capabilities.","creator":"cognitive-computations","family":"llama","tier":"","version":"2-9","type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["cognitive-computations-dolphin-llama3-2-9-8b","huggingface-llm-cognitive-dolphin-29-llama3-8b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"cognitivecomputations-dolphin-3-8b","name":"dolphin-3-8b","display_name":"Dolphin 3 8B","description":"An 8B uncensored instruction-tuned LLM from Cognitive Computations in the Dolphin series, built for general-purpose text generation.","creator":"cognitivecomputations","family":"llama","tier":"","version":"3","type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":128000,"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":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":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["cognitivecomputations-dolphin-3-8b","llamagate/dolphin3-8b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"rwkv-eagle-llama-3-8b-instruct","name":"eagle-llama-3-8b-instruct","display_name":"EAGLE Llama 3 8B Instruct","description":"An EAGLE speculative decoding draft model for Llama 3.x 8B instruct, enabling faster inference through efficient token prediction.","creator":"rwkv","family":"llama","tier":"","version":"3","type":"language","size_in_bn":8,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["accounts/fireworks/models/eagle-llama-v3-8b-instruct-v1","accounts/fireworks/models/eagle-llama-v3-8b-instruct-v2","rwkv-eagle-llama-3-8b-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":"nousresearch-hermes-llama-2-7b","name":"nousresearch-hermes-llama-2-7b","display_name":"Hermes Llama 2 7B","description":"A 7B Llama 2 fine-tune by NousResearch trained on 300,000 instructions for improved instruction-following and conversational capability.","creator":"nousresearch","family":"llama","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["huggingface-llm-nousresearch-nous-hermes-llama-2-7b","nousresearch-hermes-llama-2-7b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"nousresearch-hermes-llama2-13b","name":"nousresearch-hermes-llama2-13b","display_name":"Hermes Llama2 13B","description":"A 13B-parameter Llama 2-based LLM from Nous Research fine-tuned on over 300,000 instructions, known for long responses and low hallucination rates.","creator":"nousresearch","family":"llama","tier":"","version":null,"type":"language","size_in_bn":13,"modalities":{"input":["text"],"output":["text"]},"context_window":4096,"max_output_tokens":4096,"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":1,"ids":["accounts/fireworks/models/nous-hermes-llama2-13b","fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-13b","huggingface-llm-nousresearch-nous-hermes-llama2-13b","nousresearch-hermes-llama2-13b","nousresearch/nous-hermes-llama2-13b"],"hf_likes":322,"hf_downloads":1683,"hf_downloads_all_time":1269434,"hf_trending_score":0,"updated_at":"2026-08-12 08:02:44"},{"id":"nousresearch-hermes-llama2-70b","name":"hermes-llama2-70b","display_name":"Hermes Llama2 70B","description":"A 70B-parameter Llama 2-based LLM from Nous Research fine-tuned on over 300,000 instructions for high-quality, long-form instruction following.","creator":"nousresearch","family":"llama","tier":"","version":null,"type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":4096,"max_output_tokens":4096,"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":1,"ids":["accounts/fireworks/models/nous-hermes-llama2-70b","fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-70b","nousresearch-hermes-llama2-70b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"nousresearch-hermes-llama2-7b","name":"hermes-llama2-7b","display_name":"Hermes Llama2 7B","description":"A 7B-parameter Llama 2-based LLM from Nous Research fine-tuned on over 300,000 instructions for coherent, uncensored instruction following.","creator":"nousresearch","family":"llama","tier":"","version":null,"type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":4096,"max_output_tokens":4096,"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":1,"ids":["accounts/fireworks/models/nous-hermes-llama2-7b","fireworks_ai/accounts/fireworks/models/nous-hermes-llama2-7b","nousresearch-hermes-llama2-7b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"elyza-japanese-llama-2-13b-chat","name":"elyza-japanese-llama-2-13b-chat","display_name":"Japanese Llama 2 13B Chat","description":"A 13B-parameter Japanese-language chat LLM built on Llama 2 with additional training on Japanese corpora and instruction fine-tuning by ELYZA.","creator":"elyza","family":"llama","tier":"","version":"2","type":"language","size_in_bn":13,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["elyza-japanese-llama-2-13b-chat","huggingface-llm-elyza-japanese-llama-2-13b-chat"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"elyza-japanese-llama-2-13b-fast-chat","name":"elyza-japanese-llama-2-13b-fast-chat","display_name":"Japanese Llama 2 13B Fast Chat","description":"A faster 13B-parameter Japanese chat LLM from ELYZA based on Llama 2, optimized for lower-latency conversational inference with Japanese instruction tuning.","creator":"elyza","family":"llama","tier":"","version":"2","type":"language","size_in_bn":13,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["elyza-japanese-llama-2-13b-fast-chat","huggingface-llm-elyza-japanese-llama-2-13b-fast-chat"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"elyza-japanese-llama-2-7b-chat","name":"elyza-japanese-llama-2-7b-chat","display_name":"Japanese Llama 2 7B Chat","description":"A 7B-parameter Japanese-language chat LLM from ELYZA built on Llama 2 with additional Japanese corpus training and instruction fine-tuning.","creator":"elyza","family":"llama","tier":"","version":"2","type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["elyza-japanese-llama-2-7b-chat","huggingface-llm-elyza-japanese-llama-2-7b-chat-bf16"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"elyza-japanese-llama-2-7b-fast-chat","name":"elyza-japanese-llama-2-7b-fast-chat","display_name":"Japanese Llama 2 7B Fast Chat","description":"A faster 7B-parameter Japanese chat LLM from ELYZA based on Llama 2, optimized for efficient conversational inference in Japanese.","creator":"elyza","family":"llama","tier":"","version":"2","type":"language","size_in_bn":7,"modalities":{"input":["text"],"output":["text"]},"context_window":null,"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":false,"provider_count":0,"ids":["elyza-japanese-llama-2-7b-fast-chat","huggingface-llm-elyza-japanese-llama-2-7b-fast-chat-bf16"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-08-12 08:02:44"},{"id":"sao10k-l3-euryale-2-1-70b","name":"l3-euryale-2-1-70b","display_name":"L3 70B Euryale V2.1","description":"A 70B Llama 3-based creative roleplay model from Sao10k with strong narrative and character immersion capabilities.","creator":"sao10k","family":"llama","tier":"","version":"2-1","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":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":1,"ids":["novita/sao10k/l3-70b-euryale-v2.1","sao10k-l3-euryale-2-1-70b","sao10k/l3-70b-euryale-v2.1"],"hf_likes":167,"hf_downloads":3154,"hf_downloads_all_time":23671,"hf_trending_score":1,"updated_at":"2026-08-12 08:02:44"}],"pagination":{"page_size":50,"has_next":true,"next_token":"NTA","total_count":140},"meta":{"updated_at":"2026-08-12","request_id":"4924a51e-fe26-42f1-9fa1-1fafc4c76a4b","execution_ms":10}}