NvidiaText modelNVIDIA Nemotron 3 Ultra
NVIDIA Nemotron 3 Ultra for chat.
Model availability and access depend on your workspace and plan.
NVIDIA Nemotron 3 UltraAbout the model
NVIDIA Nemotron 3 Ultra, explained.
NVIDIA Nemotron 3 Ultra for chat.
Supported capabilities
- Chat
- Tool use
- Reasoning
What you get back. The response appears directly in your Relam chat, where you can continue the conversation.
Capabilities & limits
Inside NVIDIA Nemotron 3 Ultra.
Chat
Ask questions, give instructions and continue with follow-up messages in a conversation.
Tool use
The model can work with tools as part of a response. Relam determines which tools are available for your request and enforces their permissions.
Context window
NVIDIA Nemotron 3 Ultra has a 1,000,000-token context window. This is the model’s capacity for the text it considers in a request, including prompts and conversation context. Tokens are pieces of text, rather than a word or page count. The amount of context sent by your workspace can be lower.
Response length
The catalogue sets a maximum output of 65,536 tokens for NVIDIA Nemotron 3 Ultra. This is the response budget, distinct from its context window. Responses can be shorter depending on your request and the limits applied by your workspace.
Reasoning
NVIDIA Nemotron 3 Ultra is listed as a reasoning-capable model. Its configured reasoning levels are high, medium, none. The default level is high. Available controls depend on your workspace.
Questions & answers
More about NVIDIA Nemotron 3 Ultra.
NVIDIA Nemotron 3 Ultra for chat.
Nvidia is the vendor behind NVIDIA Nemotron 3 Ultra, a text model available in the Relam catalogue.
Ask questions, give instructions and continue with follow-up messages in a conversation.
The model can work with tools as part of a response. Relam determines which tools are available for your request and enforces their permissions.
NVIDIA Nemotron 3 Ultra has a 1,000,000-token context window. This is the model’s capacity for the text it considers in a request, including prompts and conversation context. Tokens are pieces of text, rather than a word or page count. The amount of context sent by your workspace can be lower.
The catalogue sets a maximum output of 65,536 tokens for NVIDIA Nemotron 3 Ultra. This is the response budget, distinct from its context window. Responses can be shorter depending on your request and the limits applied by your workspace.
NVIDIA Nemotron 3 Ultra is listed as a reasoning-capable model. Its configured reasoning levels are high, medium, none. The default level is high. Available controls depend on your workspace.
Open your Relam workspace and look for NVIDIA Nemotron 3 Ultra in the text model selector. Available models, controls and access depend on your workspace and plan.