{"data":[{"id":"nvidia-nemotron-super-3-120b-a12b","name":"nvidia-nemotron-super-3-120b-a12b","display_name":"Nemotron Super 3 120B A12B","description":"A 120B-parameter hybrid MoE Nemotron Super 3 model with 12B active parameters, optimized by NVIDIA for compute-efficient reasoning in specialized agentic systems.","creator":"nvidia","family":"nemotron_h","tier":"","version":"3","type":"language","size_in_bn":120,"modalities":{"input":["text"],"output":["text"]},"context_window":1000000,"max_output_tokens":235929,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2026-03-11","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":4,"ids":["accounts/fireworks/models/nvidia-nemotron-3-super-120b-a12b-fp8","accounts/fireworks/models/nvidia-nemotron-3-super-120b-a12b-nvfp4","deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","huggingface-llm-nvidia-nemotron-3-super-120b-a12b-bf16","nebius/nvidia/nemotron-3-super-120b-a12b","nvidia-nemotron-3-super-120b-a12b","nvidia-nemotron-super-3-120b-a12b","nvidia/nemotron-3-super-120b-a12b","nvidia/nemotron-3-super-120b-a12b:free","nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","openrouter/nvidia/nemotron-3-super-120b-a12b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-09-22 08:02:55"},{"id":"nvidia-nemotron-nano-3-30b-a3b","name":"nvidia-nemotron-nano-3-30b-a3b","display_name":"Nemotron Nano 3 30B A3B","description":"A 30B-parameter hybrid MoE Nemotron Nano 3 model with 3B active parameters, combining Mamba-Transformer architecture for efficient reasoning and agentic tasks.","creator":"nvidia","family":"nemotron_h","tier":"","version":"3","type":"language","size_in_bn":30,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":235929,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":"Other","capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":true,"adaptive_reasoning":false},"release_date":"2025-12-14","earliest_deprecation_date":"2026-08-24","deprecated":false,"has_pricing":true,"provider_count":5,"ids":["accounts/fireworks/models/nemotron-nano-3-30b-a3b","deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","nemotron-3-nano-30b-a3b","novita/nvidia/nemotron-3-nano-30b-a3b","nvidia-nemotron-3-nano-30b-a3b","nvidia-nemotron-3-nano-30b-a3b-reasoning","nvidia-nemotron-nano-3-30b-a3b","nvidia/nemotron-3-nano-30b-a3b","nvidia/Nemotron-3-Nano-30B-A3B","nvidia/nemotron-3-nano-30b-a3b:free","nvidia/nvidia-nemotron-3-nano-30b-a3b-bf16","openrouter/nvidia/nemotron-3-nano-30b-a3b"],"hf_likes":767,"hf_downloads":1129029,"hf_downloads_all_time":6131226,"hf_trending_score":8,"updated_at":"2026-09-22 08:02:55"},{"id":"nvidia-nemotron-3-ultra","name":"nemotron-3-ultra","display_name":"Nemotron 3 Ultra","description":"A frontier-scale Nemotron large language model from NVIDIA designed for strong agentic, reasoning, and conversational capabilities at extreme parameter counts.","creator":"nvidia","family":"nemotron_h","tier":"ultra","version":"3","type":"language","size_in_bn":null,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":false,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["accounts/fireworks/models/nemotron-3-ultra-bf16","accounts/fireworks/models/nemotron-3-ultra-nvfp4","fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4","fireworks_ai/nemotron-3-ultra-nvfp4","nvidia-nemotron-3-ultra"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-09-22 08:02:55"},{"id":"nvidia-nemotron-lightning-3-5-30b-a3b","name":"nemotron-lightning-3-5-30b-a3b","display_name":"Nemotron Lightning 3.5 30B A3B","description":"A 30B-parameter mixture-of-experts Nemotron Lightning model with 3B active parameters, built on the Nemotron-H architecture for efficient high-throughput inference.","creator":"nvidia","family":"nemotron_h","tier":"","version":"3-5","type":"language","size_in_bn":30,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"max_output_tokens":32768,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":["default"],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":false,"structured_outputs":true,"prompt_caching":true,"reasoning":true,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B","fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","fireworks_ai/nemotron-lightning-3p5-30b-a3b","huggingface-reasoning-nemotron-3-5-lightning-30b-a3b-bf16","huggingface-reasoning-nemotron-3-5-lightning-30b-a3b-nvfp4","nvidia-nemotron-lightning-3-5-30b-a3b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-09-22 08:02:55"},{"id":"nvidia-nemotron-nano-2-12b","name":"nemotron-nano-2-12b","display_name":"Nemotron Nano 2 12B","description":"A 12B-parameter hybrid LLM from NVIDIA's Nemotron Nano v2 series, trained from scratch as a unified model supporting both reasoning and non-reasoning modes.","creator":"nvidia","family":"nemotron_h","tier":"","version":"2","type":"language","size_in_bn":12,"modalities":{"input":["image","text"],"output":["text"]},"context_window":131072,"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":"2025-12-02","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":2,"ids":["accounts/fireworks/models/nvidia-nemotron-nano-12b-v2","bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2","bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2","fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-12b-v2","huggingface-reasoning-nvidia-nemotron-nano-12b-v2","nvidia-nemotron-nano-2-12b","nvidia.nemotron-nano-12b-v2","us-gov.nvidia.nemotron-nano-12b-v2"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-09-22 08:02:55"}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":5},"meta":{"updated_at":"2026-09-22","request_id":"43946d7d-7809-40e6-8f13-2fba1567cfa1","execution_ms":9}}