Small Nemotron 3 MoE for efficient coding, math, and long-context agentsNemotron 3 Nano 30B A3B by nvidia is offered by 14 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Crusoe at $0.05 / $0.20 per 1M. Prices vary about 3.9× across the providers that host it.
Median output speed is 318 tokens per second, with 0.95s to the first token.
The context window is 65,536 tokens at the reference host, but hosts report different limits, from 65,536 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-06-25.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Crusoe nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | Cloud | $0.05 | $0.20 | $0.03 | — | 262,144 ⚠ | 262,144 | |
| NanoGPT | Gateway | $0.05 | $0.20 | $0.025 | — | 262,144 ⚠ | 235,929 | |
| Novita AI | Gateway | $0.05 | $0.20 | — | — | 262,144 ⚠ | 32,768 | |
| Merge Gateway | Gateway | $0.05 | $0.20 | — | — | 256,000 ⚠ | 32,000 | |
| Eden AI deepinfra/nvidia/Nemotron-3-Nano-30B-A3B | Gateway | $0.05 | $0.20 | $0.025 | — | 262,144 ⚠ | 262,144 | |
| Deep Infra nvidia/Nemotron-3-Nano-30B-A3B | Cloud | $0.05 | $0.20 | $0.025 | — | 262,144 ⚠ | 262,144 | deprecated |
| Amazon Bedrock nvidia.nemotron-nano-3-30b | Cloud | $0.06 | $0.24 | — | — | 262,144 ⚠ | 8,192 | |
| OpenRouter | Gateway | $0.06 | $0.24 | $0.012 | — | 262,144 ⚠ | 235,929 | |
| Kilo Gateway | Gateway | $0.06 | $0.24 | $0.012 | — | 262,144 ⚠ | 235,929 | |
| Ollama Cloud nemotron-3-nano:30b | Cloud | $0.06 | $0.24 | — | — | 1,048,576 ⚠ | 131,072 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 2 of 14 providers.
4 / 14 providers expose no reasoning control (reasoning_options: []).
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.