Nemotron 3 Nano 30B A3B
NVIDIA · Open weights · Released Dec 14, 2025 · nvidia/nemotron-3-nano-30b-a3b
Best $0.06 in / $0.24 out via Nebius · fp8
262K contextToolsReasoningStructured outputPrompt cachingOpen weights
Available from 1 providerUSD / MTOK · PRICES 15 MINUTES AGO · SPEED 19 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.06 | $0.24 | $0.012 | 262K | fp8 | 1.2s | 91 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 19 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.06 / $0.24
per MTok in / out
CACHE READ $0.012
Recent changesRSS ↗
Nov 5, 2026endpoint removed · cheaperinference2 → 1
Nov 4, 2026endpoint removed · novita3 → 2
Oct 23, 2026endpoint added · cheaperinference2 → 3
Oct 9, 2026endpoint removed · deepinfra3 → 2
Oct 8, 2026endpoint removed · crusoe4 → 3
About
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...
Specifications
Context window262,144
Max output235,929
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedDec 14, 2025
TokenizerOther
WeightsHugging Face ↗
Open weights
safetensorspytorch
Related
Embed badge
[](https://modelindex.ai/models/nvidia/nemotron-3-nano-30b-a3b)Sources
OpenRouter API15 minutes ago
AGGREGATORHugging Face15 minutes ago
COMMUNITYModelIndex benchmarks19 days ago
MEASUREDVerified 15 minutes ago · list prices, not negotiated rates.