Model
Nemotron Mini 4B Instruct
Compact Nemotron model for efficient reasoning and deployable AI agents
1 providersreleased open weights
Compare providers (sorted by listed input price)
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Context | Capabilities | Status | Updated |
|---|---|---|---|---|---|---|---|---|
| Nvidia nvidia/nemotron-mini-4b-instruct | — | — | — | — | 128K | no reasoningtoolsno structuredno vision | Aug 26, 2024 |
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.