NVIDIA: Nemotron 3 Ultra
nvidia/nemotron-3-ultra-550b-a55b — available through the Autonomous Relay Agents API, served by NVIDIA NIM.
NVIDIA: Nemotron 3 Ultra has a 262,144-token context window and costs $0.625 per million input tokens and $3.125 per million output tokens, at the provider's list price on your own key.
- Context length
- 262,144 tokens
- Input
- $0.625 per M
- Output
- $3.125 per M
- Served by
- nvidia
- Input modalities
- text
Variants
The same model under another model id, priced or limited differently. Call it by its id; prices are per million tokens.
| Variant | Model id | Context | Input | Output |
|---|---|---|---|---|
| NVIDIA: Nemotron 3 Ultra (free) | nvidia/nemotron-3-ultra-550b-a55b:free | 1,000,000 | $0.00 per M | $0.00 per M |
This is a BYOK-only model: requests use your own provider key. Prices shown are the provider's list prices.
Call it
Any OpenAI-compatible client works: change the base URL and send this model id.
curl https://autonomousrelay.com/v1/chat/completions \
-H "Authorization: Bearer $AUTONOMOUS_RELAY_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "nvidia/nemotron-3-ultra-550b-a55b", "messages": [{"role": "user", "content": "Hello"}]}'