- Model
nvidia/nemotron-3-ultra-550b-a55b- Provider
together- API
openai-completions- Base URL
https://api.together.ai/v1- Input
- text
- Reasoning
- Yes
- Context window
- 512,300
- Max tokens
- 512,300
- Cost / million input
- $0.6
- Cost / million output
- $3.6
- Cost / million cache read
- $0.2
- Cost / million cache write
- $0
Model config JSON
{
"providers": {
"together": {
"apiKey": "YOUR_API_KEY",
"models": [
{
"id": "nvidia/nemotron-3-ultra-550b-a55b",
"name": "Nemotron 3 Ultra 550B A55B",
"reasoning": true,
"input": [
"text"
],
"contextWindow": 512300,
"maxTokens": 512300,
"cost": {
"input": 0.6,
"output": 3.6,
"cacheRead": 0.2,
"cacheWrite": 0
},
"compat": {
"supportsStore": false,
"supportsDeveloperRole": false,
"supportsReasoningEffort": false,
"maxTokensField": "max_tokens",
"supportsStrictMode": false,
"supportsLongCacheRetention": false,
"thinkingFormat": "together"
}
}
],
"api": "openai-completions",
"baseUrl": "https://api.together.ai/v1"
}
}
}