Nemotron 3 Nano Omni 30 B A3 B Reasoning pricing
Source: openrouter · updated 2026-11-18
Short answer: Nemotron 3 Nano Omni 30 B A3 B Reasoning is published at $0.00 per million input and output tokens — it is a free-tier model. Free tiers normally carry rate limits and are not intended for production traffic, so confirm the current terms before relying on it.
Input / 1M
Free
Output / 1M
Free
Output ÷ input
n/a (free tier)
Context window
256,000
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | Free |
| Output, per 1M tokens | Free |
| Output ÷ input multiple | n/a (free tier) |
| 3:1 blended, per 1M tokens | Free |
| Context window | 256,000 tokens |
| Vendor | nvidia |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | Free | Free | Free |
| 10M in / 2.5M out | Free | Free | Free |
| 100M in / 25M out | Free | Free | Free |
Other nvidia models
| Model | Input | Output |
|---|---|---|
| Nemotron 3.5 Super VL | Free | Free |
| Nemotron 3.5 Lightning | Free | Free |
| Nemotron 3 Ultra 550 B A55 B | Free | Free |
| Nemotron 3 Nano 30 B A3 B | $0.060 | $0.240 |
| Nemotron 3 Super 120 B A12 B | $0.075 | $0.400 |
Compare against
- Nemotron 3 Nano Omni 30 B A3 B Reasoning vs Gemma 4 26 B A4 B It
- Nemotron 3 Nano Omni 30 B A3 B Reasoning vs Nemotron 3 Ultra 550 B A55 B
Cheaper alternatives
This is the cheapest tracked model in its class. Next step up: Qwen 2.5 Coder 7 B at $0.010 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.