Compact Nemotron model for efficient reasoning and deployable AI agents
Specification
most-agreed values
Context
131K
Max output
8K
Released
2025-08-18
Knowledge cutoff
2024-09
Retires
2027-03-30
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.06
Output
$0.23
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | bedrock_converse | $0.03 |
| Batch output | bedrock_converse | $0.12 |
| Priority input | bedrock_converse | $0.11 |
| Priority output | bedrock_converse | $0.40 |
Batch input is 50% below the interactive input price at the same listing.
Available from 5 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| amazon-bedrock | $0.06 | $0.23 | — | — | 131K | 8K | — |
| bedrock_converse | $0.06 | $0.23 | — | — | 128K | 8K | 2027-03-30 |
| merge-gateway | $0.06 | $0.23 | — | — | 128K | 8K | — |
| vercel | $0.06 | $0.23 | — | — | 131K | 131K | — |
| bedrock | $0.072 | $0.276 | — | — | 128K | 8K | 2027-03-30 |
More from NVIDIA
most-hosted first