{"data":{"id":"nvidia-llama-3-1-nemotron-70b-instruct","name":"llama-3-1-nemotron-70b-instruct","display_name":"Llama 3.1 Nemotron 70B Instruct","description":"A 70B instruction-tuned LLM fine-tuned by NVIDIA on Llama 3.1 to significantly improve helpfulness and response quality on user queries.","creator":"nvidia","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":false,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":"2024-10-15","earliest_deprecation_date":"2026-05-07","deprecated":true,"has_pricing":true,"provider_count":2,"ids":["accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct","deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct","fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct","llama-3-1-nemotron-instruct-70b","nvidia-llama-3-1-nemotron-70b-instruct","nvidia/llama-3.1-nemotron-70b-instruct","nvidia/Llama-3.1-Nemotron-70B-Instruct"],"hf_likes":2064,"hf_downloads":9963,"hf_downloads_all_time":1815075,"hf_trending_score":0,"updated_at":"2026-06-19 08:02:10"},"meta":{"updated_at":"2026-06-19","request_id":"c159153c-5d87-4a25-863f-fbbfb5b50f88","execution_ms":8}}