Nemotron 3 Ultra API
nvidia/nemotron-3-ultra
Use Nemotron 3 Ultra by NVIDIA through the Solo Router API: 131K-token context and streaming. $1.17 per million input tokens and $2.21 per million output tokens, billed from prepaid credit.
Input
$1.17
per 1M tokens
Output
$2.21
per 1M tokens
Cached input
$0.234
per 1M tokens
Context window
131K
tokens
Example request
curl https://solorouter.ai/api/v1/chat/completions \ -H "Authorization: Bearer $SOLO_KEY" -H "Content-Type: application/json" \ -d '{"model": "nvidia/nemotron-3-ultra", "messages": [{"role": "user", "content": "Hello"}], "stream": true}'
More from NVIDIA
| Model | Context | Input / 1M | Output / 1M | Cached / 1M |
|---|---|---|---|---|
|
Nemotron 3.5 Super VL nvidia/nemotron-3.5-super-vl |
1M | $0.39 | $0.845 | $0.078 |
|
Nemotron 3 Nano Omni nvidia/nemotron-3-nano-omni |
66K | $0.65 | $1.17 | $0.13 |
|
Nemotron Nano 12B v2 VL nvidia/nemotron-nano-12b-v2-vl |
128K | $0.26 | $0.78 | $0.052 |
Frequently asked questions
How much does the Nemotron 3 Ultra API cost?
$1.17 per million input tokens and $2.21 per million output tokens, and $0.234 per million cached input tokens. You pay from prepaid credit with no monthly fee.
How do I get Nemotron 3 Ultra API access?
Sign in to Solo Router with Google, create an API key and set "model": "nvidia/nemotron-3-ultra" in a chat-completions request to https://solorouter.ai/api/v1.
What is the context window of Nemotron 3 Ultra?
131,072 tokens.
Get your API key in 30 seconds
Sign in with Google. New accounts get free credit (one per person) to try the models.
Get started free