Nemotron 3 Nano 30B A3B pricing & benchmarks
Nemotron 3 Nano 30B A3B is available from NVIDIA at $0.050 per million input tokens and $0.200 per million output tokens ($0.088 blended at 3:1). It accepts up to 262,144 tokens of context. NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
Pricing
Per million tokens · OpenRouter
Input$0.050
Output$0.200
Blended (3:1)$0.088
Specification
nvidia/nemotron-3-nano-30b-a3b
Context window262K
Max output262K
ReleasedDec 2025
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for Nemotron 3 Nano 30B A3B yet. We show nothing rather than reprinting an unverified figure.
Where to run Nemotron 3 Nano 30B A3B
3 hosts · all priced within ~5% of each other. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| Crusoe | $0.087 | $0.050 / $0.200 | 262K | fp8 | 99.7% |
| DeepInfra | $0.087 | $0.050 / $0.200 | 262K | fp4 | 87.8% |
| Novita | $0.087 | $0.050 / $0.200 | 262K | fp4 | 97.0% |
Host prices and uptime from OpenRouter, synced 2026-08-08. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Nemotron 3 Nano 30B A3B
Nemotron 3 Nano 30B A3B vs Qwen3.8 Max
Nemotron 3 Nano 30B A3B vs DeepSeek V4 Flash 0731
Nemotron 3 Nano 30B A3B vs Claude Opus 5
Nemotron 3 Nano 30B A3B vs Gemini 3.6 Flash
Nemotron 3 Nano 30B A3B vs Kimi K3
Nemotron 3 Nano 30B A3B vs GPT-5.6 Luna
Nemotron 3 Nano 30B A3B vs GPT-5.6 Terra
Nemotron 3 Nano 30B A3B vs GPT-5.6 Sol
FAQ
How much does Nemotron 3 Nano 30B A3B cost?
Nemotron 3 Nano 30B A3B costs $0.050 per million input tokens and $0.200 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.088 per million tokens.
What is Nemotron 3 Nano 30B A3B's context window?
Nemotron 3 Nano 30B A3B accepts up to 262,144 tokens of context, and can generate up to 262,144 output tokens.