Nemotron 3 Nano 30B A3B: API pricing, providers and specs
Nemotron 3 Nano 30B A3B is a text model by NVIDIA. 10 providers serve it, from $0.20 to $0.30 /1M; the lowest price is at Novita AI.
How Nemotron 3 Nano 30B A3B compares
Against the 737 text models on the site priced the same way.
- Cheap for its class: at $0.20 /1M, its lowest price undercuts 85% of comparable models (median $1.10).
- Its 262K-token context window is larger than 45% of them (median 262K), about 390 pages of text.
- 10 providers serve it; 77% of comparable models have fewer.
Nemotron 3 Nano 30B A3B prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 FastRouter | Free/1M | Free/1M | — | 1.05M |
 Novita AI | $0.05/1M | $0.20/1M | — | — |
| Vercel AI Gateway | $0.05/1M | $0.20/1M | $0.025/1M | 262K |
 Requesty | $0.05/1M | From$0.20/1M | — | 262K |
| AI/ML API | $0.053/1M | $0.212/1M | — | — |
| OpenRouter | $0.06/1M | From$0.24/1M | — | 262K |
 Prime Inference | $0.06/1M | $0.24/1M | — | — |
 Cortecs | $0.06/1M | $0.241/1M | — | — |
 AIHubMix | $0.066/1M | $0.264/1M | — | — |
 Venice AI | $0.075/1M | $0.30/1M | — | — |
- Novita AI$0.20
- Vercel AI Gateway$0.20
- RequestyFrom$0.20
- AI/ML API$0.212
- Prime Inference$0.24
- OpenRouterFrom$0.24
- Cortecs$0.241
- AIHubMix$0.264
- Venice AI$0.30
Specs
- Type
- Text
- Maker
- NVIDIA
- Inputs
- Text
- Outputs
- Text
- Context
- 262K≈ 390 pages of text
- Max output
- 236K
- Capabilities
- JSON, Reasoning, Tool calling
- Released
- Dec 15, 2025
- License
- —
- Open weights
- —
- Monthly searches
- 390
Alternatives to Nemotron 3 Nano 30B A3B
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Nemotron 3 Nano 30B A3Bthis model | $0.20/1M | 262K | — | 10 |
 GLM-5.3-Flash | $0.20/1M | 1.05M | 1608 | 45 |
 Qwen3.8 27B | $0.50/1M | 262K | 1591 | 33 |
| GPT-6 Luna | $0.40/1M | 1.05M | 1578 | 28 |
| Claude Haiku 5.5 | $0.30/1M | 1M | 1585 | 27 |
| Qwen3.8 Flash Next | $0.376/1M | 262K | 1628 | 5 |
 DeepSeek V4 Flash | $0.17/1M | 1.05M | — | 26 |
| DeepSeek V4 Flash Vision Exp | $0.294/1M | 1.05M | — | 26 |
| DeepSeek V4 Pro | $0.418/1M | 1.05M | — | 33 |
More from NVIDIA
Nemotron 3.5 Super VL (free)NVIDIAFree/1MNemotron 3.5 Lightning 30B A3BNVIDIA$0.16/1MNemotron 3.5 Embed 1BNVIDIAFree/1MNemotron 3.5 Super 120B A12BNVIDIA$0.50/1MNemotron 3.5 ASRNVIDIA$0.008/runNemotron 3.5 Bolt E4BNVIDIAFree/1MNemotron 3 Super 120B A12BNVIDIA$0.40/1MNemotron 3 Ultra 550B A55BNVIDIA$2.20/1MNemotron 3 Nano 30B A3B FAQ
The lowest price for Nemotron 3 Nano 30B A3B is $0.20 /1M, at Novita AI.
Novita AI, at $0.20 /1M. 10 providers serve Nemotron 3 Nano 30B A3B; the table above lists every one with its price.
Nemotron 3 Nano 30B A3B reads up to 262K tokens per request and writes up to 236K.
We have not found Nemotron 3 Nano 30B A3B's weights published by its maker.
10 API providers serve Nemotron 3 Nano 30B A3B. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us