NVIDIA Nemotron 3 Super 120B A12B
amazon-bedrock/nvidia.nemotron-super-3-120b · family nemotron · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.28
Blended $/1M (3:1)
$0.15
Input $/1M
$0.65
Output $/1M
$0.80
1M in + 1M out
—
Cache read $/1M
#2135 of 7,708
Cheapest rank
- Provider
- Amazon Bedrock (
amazon-bedrock) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“NVIDIA Nemotron 3 Super 120B A12B” is offered by 2 providers — cheapest-effective first. This one (Amazon Bedrock) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Amazon Bedrock (this) | $0.15 | $0.65 | $0.28 | 262k |
| Vercel AI Gateway | $0.15 | $0.65 | $0.28 | 256k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Amazon Bedrock 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-super-3-120b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):