{"data":{"id":"nvidia","name":"NVIDIA","website":"https://build.nvidia.com","categories":["text","audio","image","video"],"docs_url":"https://docs.nvidia.com/nim/","notes":"Live OpenRouter feed. Prices are OpenRouter list rates, not a contract with the origin lab.","role":"lab","models":[{"id":"nvidia/llama-nemotron-embed-vl-1b-v2:free","provider_id":"nvidia","name":"NVIDIA: Llama Nemotron Embed VL 1B V2 (free)","modalities":["text","image"],"context_window":131072,"family":"llama-nemotron-embed-vl-1b-v2","status":"active","description":"The Llama Nemotron Embed VL 1B V2 embedding model is optimized for multimodal question-answering retrieval. The model can embed 'documents' in the form of image, text, or image and text...","architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"supported_parameters":[],"created_at":1772045017,"canonical_slug":"nvidia/llama-nemotron-embed-vl-1b-v2-20260224","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"nvidia/llama-nemotron-rerank-vl-1b-v2:free","provider_id":"nvidia","name":"NVIDIA: Llama Nemotron Rerank VL 1B V2 (free)","modalities":["text","image"],"context_window":10240,"family":"llama-nemotron-rerank-vl-1b-v2","status":"active","description":"Llama Nemotron Rerank VL 1B V2 is a 1.7B multimodal reranking model from NVIDIA. It evaluates the relevance of document images and text against user queries, designed for vision RAG...","architecture":{"modality":"text+image->rerank","input_modalities":["text","image"],"output_modalities":["rerank"],"tokenizer":"Other","instruct_type":null},"supported_parameters":[],"created_at":1781036054,"canonical_slug":"nvidia/llama-nemotron-rerank-vl-1b-v2","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"nvidia/nemotron-3-embed-1b:free","provider_id":"nvidia","name":"NVIDIA: Nemotron 3 Embed 1B (free)","modalities":["text"],"context_window":32768,"family":"nemotron-3-embed-1b","status":"active","description":"NVIDIA Nemotron 3 Embed 1B is an open text embedding model from NVIDIA, optimized for high-throughput, low-latency retrieval. It is suited for enterprise search, RAG, code retrieval, and agentic retrieval...","architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"supported_parameters":[],"created_at":1784203294,"canonical_slug":"nvidia/nemotron-3-embed-1b-20260716","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"nvidia/nemotron-3-nano-30b-a3b","provider_id":"nvidia","name":"NVIDIA: Nemotron 3 Nano 30B A3B","modalities":["text"],"context_window":262144,"family":"nemotron-3-nano-30b-a3b","status":"active","description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1765731275,"canonical_slug":"nvidia/nemotron-3-nano-30b-a3b","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":"novita","cheapest_provider_name":"Novita","cheapest_price":0.0875,"savings_pct":16.7,"savings_basis":"openrouter"},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","provider_id":"nvidia","name":"NVIDIA: Nemotron 3 Nano Omni (free)","modalities":["text","audio","image","video"],"context_window":256000,"family":"nemotron-3-nano-omni-30b-a3b-reasoning","status":"active","description":"NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...","architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","audio","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"created_at":1777393095,"canonical_slug":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-20260428","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"nvidia/nemotron-3-super-120b-a12b","provider_id":"nvidia","name":"NVIDIA: Nemotron 3 Super","modalities":["text"],"context_window":1048576,"family":"nemotron-3-super-120b-a12b","status":"active","description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1773245239,"canonical_slug":"nvidia/nemotron-3-super-120b-a12b-20230311","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.16375,"savings_pct":80.2,"savings_basis":"openrouter"},{"id":"nvidia/nemotron-3-ultra-550b-a55b","provider_id":"nvidia","name":"NVIDIA: Nemotron 3 Ultra","modalities":["text"],"context_window":262144,"family":"nemotron-3-ultra-550b-a55b","status":"active","description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_p"],"created_at":1780551208,"canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.74,"savings_pct":29.5,"savings_basis":"openrouter"},{"id":"nvidia/nemotron-3-ultra-550b-a55b:free","provider_id":"nvidia","name":"NVIDIA: Nemotron 3 Ultra (free)","modalities":["text"],"context_window":1000000,"family":"nemotron-3-ultra-550b-a55b","status":"active","description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","seed","temperature","tool_choice","tools","top_p"],"created_at":1780551208,"canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b","provider_id":"nvidia","name":"NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B","modalities":["audio"],"context_window":0,"family":"nemotron-3.5-asr-streaming-multilingual-0.6b","status":"active","description":"Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice...","architecture":{"modality":"audio->transcription","input_modalities":["audio"],"output_modalities":["transcription"],"tokenizer":"Other","instruct_type":null},"supported_parameters":[],"created_at":1786654371,"canonical_slug":"nvidia/nemotron-3.5-asr-streaming-multilingual-0.6b-20260813","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.00000333,"savings_pct":null,"savings_basis":null},{"id":"nvidia/nemotron-3.5-content-safety","provider_id":"nvidia","name":"NVIDIA: Nemotron 3.5 Content Safety","modalities":["text","image"],"context_window":131072,"family":"nemotron-3.5-content-safety","status":"active","description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","seed","stop","temperature","top_k","top_p"],"created_at":1780581864,"canonical_slug":"nvidia/nemotron-3.5-content-safety-20260604","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.2,"savings_pct":null,"savings_basis":null},{"id":"nvidia/nemotron-3.5-content-safety:free","provider_id":"nvidia","name":"NVIDIA: Nemotron 3.5 Content Safety (free)","modalities":["text","image"],"context_window":128000,"family":"nemotron-3.5-content-safety","status":"active","description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","top_p"],"created_at":1780581864,"canonical_slug":"nvidia/nemotron-3.5-content-safety-20260604","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"nvidia/nemotron-3.5-embed-1b:free","provider_id":"nvidia","name":"NVIDIA: Nemotron 3.5 Embed 1B (free)","modalities":["text","image"],"context_window":32768,"family":"nemotron-3.5-embed-1b","status":"active","description":"Nemotron 3.5 Embed 1B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be...","architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"supported_parameters":[],"created_at":1792591670,"canonical_slug":"nvidia/nemotron-3.5-embed-1b-20261021","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"nvidia/nemotron-3.5-embed-8b:free","provider_id":"nvidia","name":"NVIDIA: Nemotron 3.5 Embed 8B (free)","modalities":["text","image"],"context_window":32768,"family":"nemotron-3.5-embed-8b","status":"active","description":"Nemotron 3.5 Embed 8B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics). Queries are text and documents can be...","architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"supported_parameters":[],"created_at":1792591666,"canonical_slug":"nvidia/nemotron-3.5-embed-8b-20261021","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"nvidia/nemotron-3.5-lightning","provider_id":"nvidia","name":"NVIDIA: Nemotron 3.5 Lightning","modalities":["text"],"context_window":262144,"family":"nemotron-3.5-lightning","status":"active","description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1786452751,"canonical_slug":"nvidia/nemotron-3.5-lightning-20260807","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":"darkbloom","cheapest_provider_name":"Darkbloom","cheapest_price":0.04875,"savings_pct":52.4,"savings_basis":"openrouter"},{"id":"nvidia/nemotron-3.5-lightning:free","provider_id":"nvidia","name":"NVIDIA: Nemotron 3.5 Lightning (free)","modalities":["text"],"context_window":1000000,"family":"nemotron-3.5-lightning","status":"active","description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["include_reasoning","max_tokens","reasoning","seed","temperature","tool_choice","tools","top_p"],"created_at":1786452751,"canonical_slug":"nvidia/nemotron-3.5-lightning-20260807","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"nvidia/nemotron-3.5-rerank-8b:free","provider_id":"nvidia","name":"NVIDIA: Nemotron 3.5 Rerank 8B (free)","modalities":["text","image"],"context_window":32768,"family":"nemotron-3.5-rerank-8b","status":"active","description":null,"architecture":{"modality":"text+image->rerank","input_modalities":["text","image"],"output_modalities":["rerank"],"tokenizer":"Other","instruct_type":null},"supported_parameters":[],"created_at":1792591657,"canonical_slug":"nvidia/nemotron-3.5-rerank-8b-20261021","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"nvidia/nemotron-3.5-super-vl","provider_id":"nvidia","name":"NVIDIA: Nemotron 3.5 Super VL","modalities":["text","image","video"],"context_window":1048576,"family":"nemotron-3.5-super-vl","status":"active","description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"created_at":1792076662,"canonical_slug":"nvidia/nemotron-3.5-super-vl-20261015","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":"darkbloom","cheapest_provider_name":"Darkbloom","cheapest_price":0.1325,"savings_pct":44.2,"savings_basis":"openrouter"},{"id":"nvidia/nemotron-3.5-super-vl:free","provider_id":"nvidia","name":"NVIDIA: Nemotron 3.5 Super VL (free)","modalities":["text","image","video"],"context_window":1000000,"family":"nemotron-3.5-super-vl","status":"active","description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...","architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"supported_parameters":["include_reasoning","max_tokens","reasoning","response_format","seed","structured_outputs","temperature","tool_choice","tools","top_p"],"created_at":1792076662,"canonical_slug":"nvidia/nemotron-3.5-super-vl-20261015","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null},{"id":"nvidia/nemotron-3.5-transcribe","provider_id":"nvidia","name":"NVIDIA: Nemotron 3.5 Transcribe","modalities":["audio"],"context_window":0,"family":"nemotron-3.5-transcribe","status":"active","description":"Nemotron 3.5 Transcribe is an open-weight speech recognition model from NVIDIA, a 30B mixture-of-experts with about 4B active parameters. It transcribes recordings of up to one hour in 40 languages,...","architecture":{"modality":"audio->transcription","input_modalities":["audio"],"output_modalities":["transcription"],"tokenizer":"Other","instruct_type":null},"supported_parameters":[],"created_at":1793235111,"canonical_slug":"nvidia/nemotron-3.5-transcribe-20261028","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":24.975,"savings_pct":null,"savings_basis":null},{"id":"nvidia/parakeet-tdt-0.6b-v3","provider_id":"nvidia","name":"NVIDIA: Parakeet TDT 0.6B v3","modalities":["audio"],"context_window":0,"family":"parakeet-tdt-0.6b-v3","status":"active","description":"Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across...","architecture":{"modality":"audio->transcription","input_modalities":["audio"],"output_modalities":["transcription"],"tokenizer":"Other","instruct_type":null},"supported_parameters":[],"created_at":1779848335,"canonical_slug":"nvidia/parakeet-tdt-0.6b-v3","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":"together","cheapest_provider_name":"Together","cheapest_price":18.75,"savings_pct":null,"savings_basis":null},{"id":"nvidia/switchyard","provider_id":"nvidia","name":"NVIDIA: Switchyard","modalities":["text"],"context_window":1000000,"family":"switchyard","status":"active","description":"Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most...","architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"supported_parameters":[],"created_at":1790025947,"canonical_slug":"nvidia/switchyard","catalog_source":"openrouter","host_id":"openrouter","host_name":"OpenRouter","creator_id":"nvidia","creator_name":"NVIDIA","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null}]}}