Nemotron-3-Ultra

NVIDIAChat & Reasoning

Nemotron 3 Ultra: text reasoning and long-context agent workflows.

API IDNemotron-3-Ultra
View setup
View usage

Overview

Context
262,144 tokens
Input
Text
Output
Text
Providers
Azure AI Foundry
Latest operational check
Healthy
API compatibility
  • OpenAI Chat Completions
Recommended for
  • General-purpose reasoning
  • Long-context analysis
  • Production assistants

Keep in mind: Text input is supported; image and audio input are unavailable. Request capacity depends on the current token rate limit.

Supported features
  • Function calling: Supported
  • Structured outputs: Supported
  • Vision: Not supported
  • Streaming: Supported
  • Reasoning: Supported
  • Prompt caching: Supported
Supported parameters
response_formatfrequency_penaltyfunction_callfunctionslogit_biaslogprobsmax_completion_tokensmax_tokensnparallel_tool_callspresence_penaltyprompt_cache_keyseedservice_tierstopstorestreamstream_optionstemperaturetool_choicetoolstop_logprobstop_p
View API reference

Make your first request

View full setup 
curl --fail-with-body https://gateway.primexos.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"Nemotron-3-Ultra","messages":[{"role":"user","content":"Hello from Primex"}],"stream":false}'

Executing this request uses your account’s API credits.

gpt-6-astraOpenAIgpt-6.1-solOpenAIgpt-6-solOpenAI