Nemotron 3 Ultra
vercel/nvidia/nemotron-3-ultra-550b-a55b · family nemotron · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$1.05
Blended $/1M (3:1)
$0.6
Input $/1M
$2.4
Output $/1M
$3.00
1M in + 1M out
$0.12 −80%
Cache read $/1M
#4159 of 7,708
Cheapest rank
- Provider
- Vercel AI Gateway (
vercel) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 65,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Nemotron 3 Ultra” is offered by 3 providers — cheapest-effective first. CoreWeave is the cheapest at $0.91 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| CoreWeave | $0.5 | $2.15 | $0.91 | 262k |
| Vercel AI Gateway (this) | $0.6 | $2.4 | $1.05 | 1M |
| DigitalOcean | $0.9 | $1.7 | $1.10 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Vercel AI Gateway and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"nvidia/nemotron-3-ultra-550b-a55b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):