Nemotron 3 Ultra 550B A55B

Models

Model details

Model
nvidia/nemotron-3-ultra-550b-a55b
Provider
nvidia
API
openai-completions
Base URL
https://integrate.api.nvidia.com/v1
Input
text
Reasoning
Yes
Context window
1,000,000
Max tokens
65,536
Cost / million input
$0.5
Cost / million output
$2.5
Cost / million cache read
$0.15
Cost / million cache write
$0

Also available from other providers

Model config JSON
{
  "providers": {
    "nvidia": {
      "apiKey": "YOUR_API_KEY",
      "models": [
        {
          "id": "nvidia/nemotron-3-ultra-550b-a55b",
          "name": "Nemotron 3 Ultra 550B A55B",
          "reasoning": true,
          "input": [
            "text"
          ],
          "contextWindow": 1000000,
          "maxTokens": 65536,
          "cost": {
            "input": 0.5,
            "output": 2.5,
            "cacheRead": 0.15,
            "cacheWrite": 0
          },
          "compat": {
            "supportsStore": false,
            "supportsDeveloperRole": false,
            "supportsReasoningEffort": false,
            "maxTokensField": "max_tokens",
            "supportsStrictMode": false,
            "supportsLongCacheRetention": false
          }
        }
      ],
      "api": "openai-completions",
      "baseUrl": "https://integrate.api.nvidia.com/v1"
    }
  }
}