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
Sold by 16 ways
| Seller | Lane | Rate |
|---|---|---|
| Crusoe cloud | standard | $0.05per Mtok in$0.2per Mtok out$0.03per Mtok cachedmodels.dev · read 2026-09-16 |
| Thinking Machines Lab api | training | $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 today | deepinfra flex | $0.036per Mtok in$0.14per Mtok out$0.018per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregator | deepinfra | $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 today | resold | $0.04per Mtok in$0.16per Mtok out$0.024per Mtok cachedinference-api.nousresearch.com · read 2026-08-25 |
| Nous Research aggregator | standard | $0.05per Mtok in$0.2per Mtok out$0.03per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| DeepInfra aggregator | standard | $0.05per Mtok in$0.2per Mtok out$0.025per Mtok cachedapi.deepinfra.com · read 2026-08-25 |
| Novita AI aggregator | standard | $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 aggregator | standard | $0.05per Mtok in$0.2per Mtok out$0.03per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | crusoe/fp8 | $0.05per Mtok in$0.2per Mtok out$0.03per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | deepinfra/fp4 | $0.05per Mtok in$0.2per Mtok out$0.025per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | novita/fp4 | $0.05per Mtok in$0.2per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | nebius/fp8 | $0.06per Mtok in$0.24per Mtok outopenrouter.ai · read 2026-08-25 |
| Vercel AI Gateway aggregator | standard | $0.05per Mtok in$0.2per Mtok out$0.025per Mtok cachedai-gateway.vercel.sh · read 2026-08-25 |
| Nebius Token Factory aggregator | standard | $0.06per Mtok in$0.24per Mtok outtokenfactory.nebius.com · read 2026-08-25 |
| ElectronHub aggregator | standard | $0.3per Mtok in$0.9per Mtok outapi.electronhub.ai · read 2026-09-09 |
Measured 3 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 53rdof 105 | Vectara Hallucination Leaderboard | Hallucination Rate | 9.6 |
| 130thof 143 | Artificial Analysis · Agentic Index | Index | 1 |
| 163rdof 184 | Artificial Analysis · Coding Index | Index | 14.4 |
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