Back to Models
N

Nemotron 3 Ultra 550B

Nemotron
by NVIDIA

Open, efficient hybrid Mamba-Transformer MoE with 1M context, excelling in agentic reasoning, coding, planning, tool calling, and more.

Free EndpointDownloadableJun 4, 2026open license

Specifications

Context Length
1M
1,000,000 tokens
Input Price
Free
per 1M tokens
Output Price
Free
per 1M tokens
Modalities
1
text→text

Capabilities

text generationchatcodereasoningfunction callingagentic

Tags

agentcodingreasoningtool-callingMoE

API Usage

1Router is fully OpenAI-compatible. Just set the base URL and use this model ID:

nvidia/nemotron-3-ultra-550b-a55b
cURL
curl https://your-site.example/api/v1/chat/completions \
  -H "Authorization: Bearer $ROUTER_USER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-ultra-550b-a55b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'