Models
One name per model, however many providers serve it.
NVIDIA: Nemotron 3.5 Transcribe
Accepts- Audio
Creates- Text
Nemotron 3.5 Transcribe is an open-weight speech recognition model from NVIDIA, a 30B mixture-of-experts with about 4B active parameters.
nvidia/nemotron-3.5-transcribeOct 29, 2026With segment and word times361 Toman a minute of audioNVIDIA: Nemotron 3.5 Embed 1B (free)
FreeAccepts- Text
CreatesNemotron 3.5 Embed 1B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics).
nvidia/nemotron-3.5-embed-1b:freeOct 21, 202633K contextFreeNVIDIA: Nemotron 3.5 Embed 8B (free)
FreeAccepts- Text
CreatesNemotron 3.5 Embed 8B is a multimodal embedding model from NVIDIA for multilingual retrieval over text and document page images (tables, charts, infographics).
nvidia/nemotron-3.5-embed-8b:freeOct 21, 202633K contextFreeNVIDIA: Nemotron 3.5 Rerank 8B (free)
FreeAccepts- Text
CreatesA NVIDIA rerank model: it orders documents by how well they answer a query.
nvidia/nemotron-3.5-rerank-8b:freeOct 21, 202633K contextFreeNVIDIA: Nemotron 3.5 Super VL
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningNVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.
nvidia/nemotron-3.5-super-vlOct 15, 20261M context54,656 Toman/M input tokens170,800 Toman/M output tokensNVIDIA: Nemotron 3.5 Super VL (free)
FreeAccepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningNVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.
nvidia/nemotron-3.5-super-vl:freeOct 15, 20261M contextFreeNVIDIA: Switchyard
Accepts- Text
Creates- Text
Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests.
nvidia/switchyardSep 21, 20261M contextPriced after the answerNVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B
Accepts- Audio
Creates- Text
Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA.
nvidia/nemotron-3.5-asr-streaming-multilingual-0.6bAug 13, 2026With segment and word times72 Toman a minute of audioNVIDIA: Nemotron 3.5 Lightning
Accepts- Text
Creates- Text
ToolsJSONReasoningNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
nvidia/nemotron-3.5-lightningAug 11, 20261M context27,328 Toman/M input tokens75,152 Toman/M output tokensNVIDIA: Nemotron 3.5 Lightning (free)
FreeAccepts- Text
Creates- Text
ToolsReasoningNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.
nvidia/nemotron-3.5-lightning:freeAug 11, 20261M contextFreeNVIDIA: Nemotron 3 Embed 1B (free)
FreeAccepts- Text
CreatesNVIDIA Nemotron 3 Embed 1B is an open text embedding model from NVIDIA, optimized for high-throughput, low-latency retrieval.
nvidia/nemotron-3-embed-1b:freeJul 16, 20264K contextFreeNVIDIA: Nemotron 3.5 Content Safety
Accepts- Text
- Image
Creates- Text
ReasoningNVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B.
nvidia/nemotron-3.5-content-safetyJun 4, 2026131K context75,152 Toman/M input tokens75,152 Toman/M output tokensNVIDIA: Nemotron 3 Ultra
Accepts- Text
Creates- Text
ToolsJSONReasoningNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).
nvidia/nemotron-3-ultra-550b-a55bJun 4, 2026262K context181,048 Toman/M input tokens795,928 Toman/M output tokensNVIDIA: Nemotron 3 Ultra (free)
FreeAccepts- Text
Creates- Text
ToolsReasoningNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).
nvidia/nemotron-3-ultra-550b-a55b:freeJun 4, 20261M contextFreeNVIDIA: Parakeet TDT 0.6B v3
Accepts- Audio
Creates- Text
Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture.
nvidia/parakeet-tdt-0.6b-v3May 27, 2026With segment and word times361 Toman a minute of audioNVIDIA: Nemotron 3 Nano Omni (free)
FreeAccepts- Text
- Image
- Audio
- Video
Creates- Text
ToolsReasoningNVIDIA 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.
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeApr 28, 2026256K contextFreeNVIDIA: Nemotron 3 Super
Accepts- Text
Creates- Text
ToolsJSONReasoningNVIDIA 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.
nvidia/nemotron-3-super-120b-a12bMar 11, 2026262K context27,328 Toman/M input tokens146,888 Toman/M output tokensNVIDIA: Nemotron 3 Nano 30B A3B
Accepts- Text
Creates- Text
ToolsJSONReasoningNVIDIA 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.
nvidia/nemotron-3-nano-30b-a3bDec 14, 2025262K context23,912 Toman/M input tokens88,816 Toman/M output tokens
18 of 581 models · Catalog updated 3 hours ago. · Free plan prices, in Toman at today's rate. Plans and prices

