Pass IndexThe State of AISign in

Nemotron 3 Nano 30B A3B

NVIDIA Nemotron 3 Nano is an open reasoning model optimized for fast, cost-efficient inference.

text → text · made by NVIDIA

$0.05$0.2per Mtok in / out
Crusoe · 10 sellers

Sold by 16 ways

SellerLaneRate
Crusoe cloudstandard$0.05per Mtok in$0.2per Mtok out$0.03per Mtok cachedmodels.dev · read 2026-09-16
Thinking Machines Lab apitraining$0.2per Mtok in$0.49per Mtok out$0.039per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25
Requesty aggregatornot on the seller's list todaydeepinfra flex$0.036per Mtok in$0.14per Mtok out$0.018per Mtok cachedrouter.requesty.ai · read 2026-08-25
Requesty aggregatordeepinfra$0.04per Mtok in$0.16per Mtok out$0.02per Mtok cachedrouter.requesty.ai · read 2026-09-14
Nous Research aggregatornot on the seller's list todayresold$0.04per Mtok in$0.16per Mtok out$0.024per Mtok cachedinference-api.nousresearch.com · read 2026-08-25
Nous Research aggregatorstandard$0.05per Mtok in$0.2per Mtok out$0.03per Mtok cachedinference-api.nousresearch.com · read 2026-09-12
DeepInfra aggregatorstandard$0.05per Mtok in$0.2per Mtok out$0.025per Mtok cachedapi.deepinfra.com · read 2026-08-25
Novita AI aggregatorstandard$0.05per Mtok in$0.2per Mtok outapi.novita.ai · read 2026-08-25
OpenRouter 5 ways$0.05per Mtok in$0.2per Mtok out$0.03per Mtok cached
OpenRouter aggregatorstandard$0.05per Mtok in$0.2per Mtok out$0.03per Mtok cachedopenrouter.ai · read 2026-08-24
OpenRouter aggregatorcrusoe/fp8$0.05per Mtok in$0.2per Mtok out$0.03per Mtok cachedopenrouter.ai · read 2026-08-25
OpenRouter aggregatordeepinfra/fp4$0.05per Mtok in$0.2per Mtok out$0.025per Mtok cachedopenrouter.ai · read 2026-08-25
OpenRouter aggregatornovita/fp4$0.05per Mtok in$0.2per Mtok outopenrouter.ai · read 2026-08-25
OpenRouter aggregatornebius/fp8$0.06per Mtok in$0.24per Mtok outopenrouter.ai · read 2026-08-25
Vercel AI Gateway aggregatorstandard$0.05per Mtok in$0.2per Mtok out$0.025per Mtok cachedai-gateway.vercel.sh · read 2026-08-25
Nebius Token Factory aggregatorstandard$0.06per Mtok in$0.24per Mtok outtokenfactory.nebius.com · read 2026-08-25
ElectronHub aggregatorstandard$0.3per Mtok in$0.9per Mtok outapi.electronhub.ai · read 2026-09-09

Measured 3 standings

PlaceBoardMetricScore
53rdof 105Vectara Hallucination LeaderboardHallucination Rate9.6
130thof 143Artificial Analysis · Agentic IndexIndex1
163rdof 184Artificial Analysis · Coding IndexIndex14.4

About

Nemotron 3 Nano 30B A3B — a text model from NVIDIA, sold by 10 companies from $0.05 in and $0.2 out per million tokens, placed 53rd of 105 on Vectara Hallucination Leaderboard.

It takes text and returns text, with a context window of 262,144 tokens. It was published in April 2025, trained on material up to September 2024. Its sellers say it can reason step by step and call a tool. The catalogue files it under chat. Ten companies sell it. The cheapest is $0.05 in and $0.2 out per million tokens at Crusoe. Beside the standard rate there are regional and separately routed lanes. It has been measured on 3 boards, and stands best at 53rd of 105 on Vectara Hallucination Leaderboard.

Every current figure

Maker
NVIDIA
Register
model
Takes
text
Returns
text
Context
262,144 tokens
Published
April 2025
Knowledge to
September 2024
Parameters
32 billion
Licence
not read
Sellers
10
Maker's own price
not read
Price
$0.05 in and $0.2 out per million tokens — Crusoe
Boards
3
Best place
53rd of 105 — Vectara Hallucination Leaderboard

Known as 5 names

nvidia/Nemotron-3-Nano-30B-A3Bnvidia/NVIDIA-Nemotron-3-Nano-30B-A3Bdeepinfra/nvidia/Nemotron-3-Nano-30B-A3Bdeepinfra/nvidia/Nemotron-3-Nano-30B-A3B:flexnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16