Models / Nvidia / Nemotron 3 Nano 30B A3B
Nvidia · nemotron
Nemotron 3 Nano 30B A3B
Small Nemotron 3 MoE for efficient coding, math, and long-context agents
$0.05 in · $0.20 out
per 1M tokens · provider rate closest to the median. No first-party Nvidia price was listed. The reference price is Crusoe's rate, the provider closest to the median.
Provider input prices run from $0.05 to $0.17 per 1M tokens. Output prices run from $0.20 to $0.68.
- Context
- 262,144
- Max output
- 262,144
- Cache read
- $0.03
- Cache write
- —
- Reasoning
- Yes
- Tool calls
- Yes
- Structured output
- Unknown
- Vision
- No
- Open weights
- Yes
- License
- —
- Released
- Dec 15, 2025
- Updated in source
- Dec 15, 2025
- Knowledge
- —
- Providers
- 17
Providers
| Provider | Input | Output | Cache read | Cache write | Status |
|---|---|---|---|---|---|
| Crusoereference | $0.05 | $0.20 | $0.03 | — | — |
| Deep Infra | $0.05 | $0.20 | $0.025 | — | deprecated |
| Eden AI | $0.05 | $0.20 | $0.025 | — | — |
| Kilo Gateway | $0.05 | $0.20 | — | — | — |
| Merge Gateway | $0.05 | $0.20 | — | — | — |
| Novita AI | $0.05 | $0.20 | — | — | — |
| Pioneer | $0.05 | $0.20 | $0.05 | $0.05 | — |
| Vercel AI Gateway | $0.05 | $0.20 | $0.025 | — | — |
| Amazon Bedrock | $0.06 | $0.24 | — | — | — |
| Infomaniak | $0.06 | $0.25 | — | — | beta |
| Ollama Cloud | $0.06 | $0.24 | — | — | — |
| OpenRouter | $0.06 | $0.24 | — | — | — |
| Venice AI | $0.075 | $0.30 | — | — | — |
| NanoGPT | $0.17 | $0.68 | $0.085 | — | — |
| DigitalOcean | — | — | — | — | — |
| Kenari | $0 | $0 | — | — | — |
| Nvidia | $0 | $0 | — | — | deprecated |
Jobs this model qualifies for
- Coding agents — clears the bar
- Long-document Q&A — clears the bar
- Cheapest summarization — clears the bar