Nemotron 3 Nano 30B A3B
NVIDIA · Open weights · Released Dec 14, 2025 · nvidia/nemotron-3-nano-30b-a3b
Best $0.05 in / $0.20 out via DeepInfra · fp4
262K contextToolsReasoningStructured outputPrompt cachingOpen weights
Available from 3 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 8 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.05 | $0.20 | $0.025 | 262K | fp4 | 1.2s | 114 tok/s | 64.1% | |
| $0.05 | $0.20 | — | 262K | fp4 | 1.1s | 268 tok/s | 100.0% | |
| $0.06 | $0.24 | — | 262K | fp8 | 0.56s | 79 tok/s | 98.3% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 8 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.05 / $0.20
per MTok in / out
CACHE READ $0.025
Recent changesRSS ↗
Oct 8, 2026endpoint removed · crusoe4 → 3
Aug 24, 2026endpoint added · nebius3 → 4
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 API23 minutes ago
AGGREGATORHugging Face23 minutes ago
COMMUNITYModelIndex benchmarks8 days ago
MEASUREDVerified 23 minutes ago · list prices, not negotiated rates.