Nemotron 3 Ultra

nvidia/nemotron-3-ultra-550b-a55b

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

Input

$0.65 / 1M tokens

Output

$2.86 / 1M tokens

Context

1000K tokens

Capabilities

✓ Streaming✓ Tool / function calling✓ JSON / structured output○ Vision (image input)

Call this model

Pass nvidia/nemotron-3-ultra-550b-a55b as the model. Change only the base URL from your existing OpenAI SDK setup.

quickstart.sh

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

Prices are final — the routing margin is already included. See the full pricing table or the API docs.