Nemotron 3 Super API Pricing
Nemotron 3 Super by NVIDIA costs $0.15 per million input tokens and $0.65 per million output tokens on AWS Bedrock.
Price verified from AWS Bedrock's pricing page.
Rates and limits
- Input / 1M
- $0.15
- Output / 1M
- $0.65
- Cached input / 1M
- Not listed
- Batch discount
- 50% off
- Context window
- 262K tokens
- Released
- October 2025
Pricing note: Open-weight model; NVIDIA publishes no per-token price. Price is AWS Bedrock on-demand (standard tier) for "NVIDIA Nemotron 3 Super 120B A12B" in US East (N. Virginia), from the AWS Price List API ($0.00015 / $0.00065 per 1K input/output tokens; batch and flex $0.000075 / $0.000325; priority $0.0002625 / $0.0011375). DeepInfra lists it at $0.085 / $0.40.
What Nemotron 3 Super costs per month
Token volume split 3:1 between input and output, with no prompt caching.
| Tokens per month | Input / output | Standard | Batch API |
|---|---|---|---|
| 1M | 750K / 250K | $0.28 | $0.14 |
| 10M | 7.5M / 2.5M | $2.75 | $1.38 |
| 100M | 75M / 25M | $27.50 | $13.75 |
Where to run Nemotron 3 Super
Prices above are AWS Bedrock's rates. Other platforms can charge differently; the cloud platform view compares them.
- AWS BedrockCloud / platform
- OpenRouterCloud / platform
Nemotron 3 Super pricing FAQ
How much does Nemotron 3 Super cost per million tokens?
Nemotron 3 Super costs $0.15 per million input tokens and $0.65 per million output tokens, as listed on AWS Bedrock's pricing page on September 30, 2026.
How much does Nemotron 3 Super cost for 10 million tokens a month?
About $2.75 a month, assuming 7.5 million input and 2.5 million output tokens with no prompt caching, or $1.38 through the batch API.
What is the context window of Nemotron 3 Super?
Nemotron 3 Super accepts up to 262,144 tokens of context.
Does Nemotron 3 Super support prompt caching?
No cached-input price is listed for Nemotron 3 Super, so repeated prompt prefixes are billed at the standard input rate.
Is there a batch discount for Nemotron 3 Super?
Yes. Requests sent through the batch API cost 50% less: $0.075 per million input tokens and $0.325 per million output tokens.
Where can I use the Nemotron 3 Super API?
Nemotron 3 Super is available through AWS Bedrock and OpenRouter.
Compare with other models
Prices shown as input / output per million tokens. All model prices · Side-by-side comparison