NVIDIA · nemotron family
Small Nemotron 3 MoE for efficient coding, math, and long-context agents
Provider-specific prices and limits stay separate from canonical model facts.
| Provider | Provider model ID | Input | Output | Context | Output limit |
|---|---|---|---|---|---|
| NanoGPT | nvidia/nemotron-3-nano-30b-a3b | $0.17 / 1M | $0.68 / 1M | 256,000 | 262,144 |
| Nvidia | nvidia/nemotron-3-nano-30b-a3b | $0 / 1M | $0 / 1M | 131,072 | 131,072 |
| Kilo Gateway | nvidia/nemotron-3-nano-30b-a3b | $0.05 / 1M | $0.2 / 1M | 262,144 | 52,429 |
| Deep Infra | nvidia/Nemotron-3-Nano-30B-A3B | $0.05 / 1M | $0.2 / 1M | 262,144 | 262,144 |
| OpenRouter | nvidia/nemotron-3-nano-30b-a3b | $0.05 / 1M | $0.2 / 1M | 262,144 | 228,000 |
| Vercel AI Gateway | nvidia/nemotron-3-nano-30b-a3b | $0.05 / 1M | $0.24 / 1M | 262,144 | 262,144 |
Attachments
No
Reasoning
Yes
Tool calling
Yes
Structured output
Unknown
Temperature
Yes