Model prices / NVIDIA / Nemotron 3 Nano 30B A3B
Nemotron 3 Nano 30B A3BOpen weights
NVIDIA · released 2025-12-15
No price from the maker itself is on record for Nemotron 3 Nano 30B A3B. The lowest of 16 providers is Crusoe: $0.05 per 1M input tokens and $0.2 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 262K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
 CrusoeLowestnvidia/ | $0.05 | $0.2 | $0.03 | Lowest | Official docs |
EEden AIdeepinfra/ | $0.05 | $0.2 | $0.025 | Official docs | |
MMerge Gatewaynvidia/ | $0.05 | $0.2 | — | Official docs | |
 Novita AInvidia/ | $0.05 | $0.2 | — | Official docs | |
 Vercel AI Gatewaynvidia/ | $0.05 | $0.2 | $0.025 | Official docs | |
 Amazon Bedrocknvidia. | $0.06 | $0.24 | — | Official docs | |
CCortecsnvidia-nemotron-3-nano-30b-a3b | $0.06 | $0.24 | — | Official docs | |
KKilo Gatewaynvidia/ | $0.06 | $0.24 | $0.012 | Official docs | |
 Ollama Cloudnemotron-3-nano: | $0.06 | $0.24 | — | Official docs | |
 OpenRouternvidia/ | $0.06 | $0.24 | $0.012 | Official docs | |
 Venice AInvidia-nemotron-3-nano-30b-a3b | $0.075 | $0.3 | — | Official docs | |
TThinking Machinesnvidia/ | $0.195 | $0.495 | $0.039 | Official docs |
4 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
NNanoGPTnvidia/ | $0.17 | $0.68 | $0.085 | Official docs | |
 Deep InfraDeprecatednvidia/ | $0.05 | $0.2 | $0.025 | Deprecated | Official docs |
IInfomaniakDeprecatednvidia/ | $0.06 | $0.25 | — | Deprecated | Official docs |
KKenariDeprecatednemotron-3-nano-30b-a3b | — | — | — | Deprecated | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Small Nemotron 3 MoE for efficient coding, math, and long-context agents
Description from models.dev.
Specs
- Type
- Text
- Context
- 262K
- Max output
- 262K
- Input
- Text
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-06-25
- Open weights
- Yes
- Released
- 2025-12-15
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.