Loading
RedRouterRedRouter

Nemotron 3 Ultra

nemotron-3-ultraAvailable

NVIDIA's Nemotron 3 Ultra for chat and tool use, with a 262K context window.

Input
$0.63
Cached input
$0.13
Output
$2.77

per 1M tokens

Context
262K
Max output
8.2K
Tool callingJSON outputOpenAI Chat CompletionsOpenAI ResponsesAnthropic Messages

Quickstart

Base URLhttps://redrouter.org/v1
Model IDnemotron-3-ultra
curl 'https://redrouter.org/v1/chat/completions' \
  -H "Authorization: Bearer $REDROUTER_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"messages":[{"content":"Hello","role":"user"}],"model":"nemotron-3-ultra"}'

Set REDROUTER_API_KEY to a key from API Keys.

Supported parameters

modelmessagesstreamstream_optionsmax_tokensmax_completion_tokenstemperaturetop_pstoppresence_penaltyfrequency_penaltyseedtoolstool_choiceparallel_tool_callsresponse_formatuserreasoning_effortreasoningenable_thinkingthinkingthinking_budgetchat_template_kwargsoutput_config

Other parameters return HTTP 400; user is accepted but not forwarded. Request fields and limits.