{"data":[{"id":"nvidia-nemotron-3-ultra-550b-a55b","name":"nemotron-3-ultra-550b-a55b","display_name":"Nemotron 3 Ultra 550B A55B","description":"A 550B-parameter mixture-of-experts Nemotron model with 55B active parameters, built for frontier-scale reasoning, tool use, and agentic tasks.","creator":"nvidia","family":"nemotron","tier":"ultra","version":"3","type":"language","size_in_bn":550,"modalities":{"input":["text"],"output":["text"]},"context_window":1000000,"max_output_tokens":65536,"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":"2026-06-04","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["nvidia-nemotron-3-ultra-550b-a55b","amazon_sagemaker/huggingface-reasoning-nvidia-nemotron-3-ultra-550b-a55b-nvfp4","artificialanalysis/nvidia-nemotron-3-ultra-550b-a55b","deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","openrouter/nvidia/nemotron-3-ultra-550b-a55b","openrouter/nvidia/nemotron-3-ultra-550b-a55b:free","vercel/nvidia/nemotron-3-ultra-550b-a55b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-cascade-2-30b-a3b","name":"nemotron-cascade-2-30b-a3b","display_name":"Nemotron Cascade 2 30B A3B","description":"A 30B-parameter cascaded Nemotron model from NVIDIA with 3B active parameters, designed for efficient multi-stage reasoning and inference pipelines.","creator":"nvidia","family":"nemotron","tier":"","version":"2","type":"language","size_in_bn":30,"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":["nvidia-nemotron-cascade-2-30b-a3b","nemotron-cascade-2-30b-a3b","artificialanalysis/nemotron-cascade-2-30b-a3b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-nano-3-30b-a3b-reasoning","name":"nvidia-nemotron-nano-3-30b-a3b-reasoning","display_name":"Nemotron Nano 3 30B A3B Reasoning","description":"A reasoning-specialized 30B-parameter hybrid MoE Nemotron Nano 3 model with 3B active parameters, designed for complex multi-step inference in agentic systems.","creator":"nvidia","family":"nemotron","tier":"","version":"3","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":["nvidia-nemotron-nano-3-30b-a3b-reasoning","nvidia-nemotron-3-nano-30b-a3b-reasoning","artificialanalysis/nvidia-nemotron-3-nano-30b-a3b-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-nemotron-nano-3-30b-a3b-omni","name":"nvidia-nemotron-nano-3-30b-a3b-omni","display_name":"Nemotron Nano 3 30B A3B Omni","description":"An open multimodal Mixture-of-Experts model from NVIDIA with 30B total and 3B active parameters, capable of reasoning across text, images, video, and audio inputs.","creator":"nvidia","family":"nemotron","tier":"","version":"3","type":"language","size_in_bn":30,"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":["nvidia-nemotron-nano-3-30b-a3b-omni","nemotron-3-nano-omni-30b-a3b","artificialanalysis/nemotron-3-nano-omni-30b-a3b","fireworks/accounts/fireworks/models/nvidia-nemotron-3-nano-omni-30b-a3b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-nano-2-12b-vl-reasoning","name":"nvidia-nemotron-nano-2-12b-vl-reasoning","display_name":"Nemotron Nano 2 12B VL Reasoning","description":"A reasoning-specialized 12B-parameter vision-language variant of NVIDIA's Nemotron Nano v2, designed for complex visual and document reasoning tasks.","creator":"nvidia","family":"nemotron","tier":"","version":"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":["nvidia-nemotron-nano-2-12b-vl-reasoning","nvidia-nemotron-nano-12b-v2-vl-reasoning","artificialanalysis/nvidia-nemotron-nano-12b-v2-vl-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-nemotron-nano-2-9b-reasoning","name":"nvidia-nemotron-nano-2-9b-reasoning","display_name":"Nemotron Nano 2 9B Reasoning","description":"A reasoning-focused 9B-parameter variant of NVIDIA's Nemotron Nano v2, optimized for extended chain-of-thought inference and complex problem solving.","creator":"nvidia","family":"nemotron","tier":"","version":"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":["nvidia-nemotron-nano-2-9b-reasoning","nvidia-nemotron-nano-9b-v2-reasoning","artificialanalysis/nvidia-nemotron-nano-9b-v2-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-nemotron-nano-3-4b","name":"nvidia-nemotron-nano-3-4b","display_name":"Nemotron Nano 3 4B","description":"A compact 4B-parameter third-generation Nemotron Nano model from NVIDIA, designed for efficient on-device reasoning and instruction-following tasks.","creator":"nvidia","family":"nemotron","tier":"","version":"3","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":["nvidia-nemotron-nano-3-4b","nvidia-nemotron-3-nano-4b","artificialanalysis/nvidia-nemotron-3-nano-4b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-120b-a12b","name":"nemotron-120b-a12b","display_name":"Nemotron 120B A12B","description":"A 120B-parameter hybrid Mixture-of-Experts LLM from NVIDIA with 12B active parameters, designed for compute-efficient reasoning and agentic workloads.","creator":"nvidia","family":"nemotron","tier":"","version":null,"type":"language","size_in_bn":120,"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":true,"provider_count":1,"ids":["nvidia-nemotron-120b-a12b","baseten/nvidia/Nemotron-120B-A12B","litellm/baseten/nvidia/Nemotron-120B-A12B"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-3","name":"nemotron-3","display_name":"Nemotron 3","description":"The third-generation Nemotron LLM from NVIDIA, designed for multilingual text generation, coding, and instruction-following tasks.","creator":"nvidia","family":"nemotron","tier":"","version":"3","type":"language","size_in_bn":null,"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":["nvidia-nemotron-3","google_vertex_nvidia/publishers/nvidia/models/nemotron-v3"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-3-nano-30b-a3b","name":"nemotron-3-nano-30b-a3b","display_name":"Nemotron 3 Nano 30B A3B","description":"A 30B-parameter mixture-of-experts Nemotron model with 3B active parameters, optimized for efficient reasoning tasks.","creator":"nvidia","family":"nemotron","tier":"nano","version":"3","type":"language","size_in_bn":30,"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":["nvidia-nemotron-3-nano-30b-a3b","amazon_sagemaker/huggingface-reasoning-nvidia-nemotron-3-nano-30b-a3b-bf16"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-3-super","name":"nemotron-3-super","display_name":"Nemotron 3 Super","description":"A Super-tier variant of NVIDIA's third-generation Nemotron, optimized for high compute efficiency in multi-agent and specialized agentic applications.","creator":"nvidia","family":"nemotron","tier":"super","version":"3","type":"language","size_in_bn":null,"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":["nvidia-nemotron-3-super","google_vertex_nvidia/publishers/nvidia/models/nemotron-3-super"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-3-super-120b","name":"nemotron-3-super-120b","display_name":"Nemotron 3 Super 120B","description":"A 120B-parameter Super-tier Nemotron 3 model from NVIDIA, engineered for maximum compute efficiency and accuracy in agentic and multi-agent systems.","creator":"nvidia","family":"nemotron","tier":"super","version":"3","type":"language","size_in_bn":120,"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":["nvidia-nemotron-3-super-120b","google_vertex_nvidia/publishers/nvidia/models/nemotron-v3-super-120b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-3-super-120b-a12b","name":"nemotron-3-super-120b-a12b","display_name":"Nemotron 3 Super 120B A12B","description":"A 120B-parameter hybrid MoE Nemotron 3 Super model with 12B active parameters, optimized by NVIDIA for reasoning-intensive agentic and production workloads.","creator":"nvidia","family":"nemotron","tier":"super","version":"3","type":"language","size_in_bn":120,"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":["nvidia-nemotron-3-super-120b-a12b","amazon_sagemaker/huggingface-reasoning-nvidia-nemotron-3-super-120b-a12b-fp8","fireworks/accounts/fireworks/models/nemotron-3-super-120b-a12b-bf16"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-3-5-0-6b-asr-streaming-multilingual","name":"nemotron-3-5-0-6b-asr-streaming-multilingual","display_name":"Nemotron 3.5 0.6B ASR Streaming Multilingual","description":"A compact 0.6B-parameter FastConformer-RNNT streaming ASR model optimized for low-latency multilingual transcription across 40+ languages.","creator":"nvidia","family":"nemotron","tier":"","version":"3-5","type":"speech-to-text","size_in_bn":0.6,"modalities":{"input":["audio"],"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":["nvidia-nemotron-3-5-0-6b-asr-streaming-multilingual","deepinfra/nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-3-5-content-safety","name":"nemotron-3-5-content-safety","display_name":"Nemotron 3.5 Content Safety","description":"A multimodal safety classifier from NVIDIA that handles text and images with support for custom policies, outputting safe/unsafe classifications for content moderation.","creator":"nvidia","family":"nemotron","tier":"","version":"3-5","type":"language","size_in_bn":null,"modalities":{"input":["image","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":["default"],"tokenizer":"Other","capabilities":{"function_calling":false,"parallel_function_calling":false,"structured_outputs":false,"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":"2026-06-04","earliest_deprecation_date":null,"deprecated":false,"has_pricing":false,"provider_count":0,"ids":["nvidia-nemotron-3-5-content-safety","deepinfra/nvidia/Nemotron-Content-Safety-3.5","openrouter/nvidia/nemotron-3.5-content-safety:free"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-4-15b","name":"nvidia-nemotron-4-15b","display_name":"Nemotron 4 15B","description":"A 15B-parameter multilingual LLM from NVIDIA's Nemotron-4 generation, trained on 8 trillion tokens for text generation, coding, and multilingual tasks.","creator":"nvidia","family":"nemotron","tier":"","version":"4","type":"language","size_in_bn":15,"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":["nvidia-nemotron-4-15b","amazon_sagemaker/nvidia-nemotron-4-15b-nim"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-nano-3-30b","name":"nemotron-nano-3-30b","display_name":"Nemotron Nano 3 30B","description":"A 30B-parameter hybrid MoE Nemotron Nano model from NVIDIA's third generation, optimized for fast and cost-efficient reasoning in agentic production workloads.","creator":"nvidia","family":"nemotron","tier":"","version":"3","type":"language","size_in_bn":30,"modalities":{"input":["text"],"output":["text"]},"context_window":262144,"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":true,"adaptive_reasoning":false},"release_date":"2025-12-23","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["nvidia-nemotron-nano-3-30b","nvidia.nemotron-nano-3-30b","amazon_bedrock/nvidia.nemotron-nano-3-30b","amazon_bedrock_global/nvidia.nemotron-nano-3-30b","amazon_sagemaker/nvidia-nim-nemotron-3-nano-30b","litellm/nvidia.nemotron-nano-3-30b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-nano-3-30b-a3b-omni-reasoning","name":"nvidia-nemotron-nano-3-30b-a3b-omni-reasoning","display_name":"Nemotron Nano 3 30B A3B Omni Reasoning","description":"A reasoning-optimized variant of NVIDIA's Nemotron Nano Omni multimodal MoE model, combining 30B total and 3B active parameters with extended chain-of-thought capabilities across text, image, video, and audio.","creator":"nvidia","family":"nemotron","tier":"","version":"3","type":"language","size_in_bn":30,"modalities":{"input":["audio","image","text","video"],"output":["text"]},"context_window":256000,"max_output_tokens":65536,"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":false,"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":"2026-04-28","earliest_deprecation_date":null,"deprecated":false,"has_pricing":false,"provider_count":0,"ids":["nvidia-nemotron-nano-3-30b-a3b-omni-reasoning","amazon_sagemaker/huggingface-vlm-nvidia-nemotron3-nano-omni-30ba3b-reasoning-fp8","deepinfra/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-nano-8b","name":"nvidia-nemotron-nano-8b","display_name":"Nemotron Nano 8B","description":"An 8B-parameter Nemotron Nano LLM derived from Llama 3.1, adding reasoning capabilities to a compact model suited for efficient deployment.","creator":"nvidia","family":"nemotron","tier":"","version":null,"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":["nvidia-nemotron-nano-8b","amazon_sagemaker/nvidia-nemotron-nano-8b-nim"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-parse","name":"nvidia-nemotron-parse","display_name":"Nemotron Parse","description":"A document-parsing model from NVIDIA's Nemotron family that extracts formatted text and bounding boxes from document images for structured information retrieval.","creator":"nvidia","family":"nemotron","tier":"","version":null,"type":"language","size_in_bn":null,"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":["nvidia-nemotron-parse","amazon_sagemaker/nvidia-nemotron-parse"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-super-1-5-49b","name":"nvidia-nemotron-super-1-5-49b","display_name":"Nemotron Super 1.5 49B","description":"A 49B-parameter Nemotron Super v1.5 LLM from NVIDIA, derived from Llama 3.3 70B and optimized for reasoning, RAG, and tool-calling in agentic workflows.","creator":"nvidia","family":"nemotron","tier":"","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":["nvidia-nemotron-super-1-5-49b","amazon_sagemaker/nvidia-nemotron-super-49b-nim-1-5"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-super-3-120b","name":"nemotron-super-3-120b","display_name":"Nemotron Super 3 120B","description":"A 120B-parameter third-generation Nemotron Super model from NVIDIA, engineered for highest compute efficiency and accuracy in multi-agent applications.","creator":"nvidia","family":"nemotron","tier":"","version":"3","type":"language","size_in_bn":120,"modalities":{"input":["text"],"output":["text"]},"context_window":256000,"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":false,"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":"2026-03-18","earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":1,"ids":["nvidia-nemotron-super-3-120b","nvidia.nemotron-super-3-120b","amazon_bedrock/nvidia.nemotron-super-3-120b","amazon_bedrock_global/nvidia.nemotron-super-3-120b","litellm/nvidia.nemotron-super-3-120b"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"},{"id":"nvidia-nemotron-super-49b","name":"nvidia-nemotron-super-49b","display_name":"Nemotron Super 49B","description":"A large language model derived from Meta Llama 3.3 70B Instruct, optimized for reasoning tasks with a 49B parameter footprint.","creator":"nvidia","family":"nemotron","tier":"","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":["nvidia-nemotron-super-49b","amazon_sagemaker/nvidia-nemotron-super-49b-nim"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-07 08:02:45"}],"pagination":{"page_size":50,"has_next":false,"next_token":null,"total_count":23},"meta":{"updated_at":"2026-06-07","request_id":"71f523f6-9aa7-4d7e-8416-6a90d39ef325","execution_ms":8}}