Nemotron 3 Ultra 550B A55B
Text model by NVIDIA, available through the Foza OpenAI-compatible API.
Providers
1
Input from
$0.05/M
Output from
$0.15/M
Max context
—
Best latency
81.2s
Tokens processed
0
Providers (1)
Compare price, context and speed across providers serving this model. Select a row to update the code sample.
| Provider | Input | Output | Context | Max output | Latency | Success | Requests | AI check | |
|---|---|---|---|---|---|---|---|---|---|
CIN_B Cheapest | $0.05/M | $0.15/M | — | — | 81.2s | 0.0% | 2 | — | Subscribe |
Quick start
OpenAI-compatible API. Use "cinb/nemotron-3-ultra" as the model name after subscribing your API key.
curl https://api.foza.ai/v1/chat/completions \
-H "Authorization: Bearer $FOZA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "cinb/nemotron-3-ultra",
"messages": [{ "role": "user", "content": "Hello" }]
}'Specifications
- Author
- NVIDIA
- Category
- Text
- Input modalities
- Text
- Output modalities
- Text
- Parameters
- 560.5B
- Max context
- —
- Released
- 2026-06-03
- Catalog ID
- nvidia/nemotron-3-ultra-550b-a55b