Skip to content
nvidia/nemotron-3-ultra-550b-a55b

1M context · Jun 2026 · 11 upstreams

NVIDIA Nemotron-3-Ultra-550B-A55B is a 550B parameter (55B active) frontier model built on a LatentMoE hybrid architecture combining Mamba-2, MoE, and Attention with Multi-Token Prediction. Features a 1M token context window, configurable reasoning mode (enable_thinking), and strong multilingual support across English, French, Spanish, Italian, German, Japanese, Korean, Hindi, Brazilian Portuguese, and Chinese. Best suited for complex agentic workflows, long-context analysis, tool use, and high-stakes RAG.

context
1M
input / 1M
$0
output / 1M
$0
routes
12
speed, 24h
—

Upstreams

12
  1. 1NVIDIAPlatform · freeFreeTPS —TTFT ——
  2. 2AIHubMixYour key · not addedyour planTPS —TTFT ——
  3. 3NVIDIAYour key · not addedyour planTPS —TTFT ——
  4. 4OpenRouterYour key · not addedyour planTPS —TTFT ——
  5. 5OpenRouterYour key · not addedyour planTPS —TTFT ——
  6. 6Ollama CloudYour key · not addedyour planTPS —TTFT ——
  7. 7BasetenYour key · not addedyour planTPS —TTFT ——
  8. 8CommandCodeYour key · not addedyour planTPS —TTFT ——
  9. 9Ramp RouterYour key · not addedyour planTPS —TTFT ——
  10. 10Vercel AI GatewayYour key · not addedyour planTPS —TTFT ——
  11. 11GMICloudYour key · not addedyour planTPS —TTFT ——
  12. 12Nous ResearchYour key · not addedyour planTPS —TTFT ——

Try it

Send a prompt

Uptime, last 48 hours

No health checks yet.

  • Up
  • No traffic
  • Down

Details

Owner
NVIDIA
Kind
Chat
Released
Jun 2026
Context
1M
Data policy
Provider retention
Endpoint
/api/v1/chat/completions

Quick start

curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "nvidia/nemotron-3-ultra-550b-a55b",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'