MDL
Nemotron 3 Nano Omni 30B A3B Reasoning
NVIDIA
Verified against Artificial Analysis · Jul 13, 2026
Capability
56
percentile index
Price /M
$0.075 / $0.3
in / out
Context
—
Avg score
33.2
7 benchmarks
AA Intelligence
14.9
index
Speed
323 tok/s
TTFT 0.5s
Released
Apr 29, 2026
About
Nemotron 3 Nano Omni 30B A3B Reasoning is a open-weights model in the Nemotron family from NVIDIA. Benchmarked on 7 evals, averaging 33.2.
Benchmark scores · 7
avg 33.2 — higher is betterThe research behind this model
all papers mentioning it →Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning▲ 15 on HF · Jun 12, 2026ProCUA-SFT Technical Report▲ 9 on HF · Jun 15, 2026Diagnosing Overhead in Dispatch Operations: Cross-architecture ObservatoryMay 20, 2026Mixture of Experts for Low-Resource LLMsMay 17, 2026HEBATRON: A Hebrew-Specialized Open-Weight Mixture-of-Experts Language ModelMay 11, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed323 tok/s
Latency (TTFT)0.5s
First answer6.7s
Price in / out$0.075 / $0.3 per 1M
Blended price$0.131 / 1M
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$0.3/M