Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
Specification
most-agreed values
Context
1M
Max output
128K
Released
2026-06-04
Knowledge cutoff
2025-09
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.50
Output
$2.20
Cache read
$0.10
Available from 4 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| llmgateway | $0.50 | $2.20 | $0.10 | — | 1M | 128K | — |
| llmgateway-providers | $0.50 | $2.20 | $0.10 | — | 262K | 262K | — |
| kyma · kyma | $0.675 | $3.375 | $0.135 | — | 1M | 33K | — |
| digitalocean | $0.90 | $1.70 | $0.18 | — | 131K | 131K | — |
Other listings of this model
same model, different key
More from NVIDIA
most-hosted first