Nemotron 3 Nano 30B A3B vs Nemotron 3 Nano Omni (free)
Nemotron 3 Nano 30B A3B (NVIDIA) and Nemotron 3 Nano Omni (free) (NVIDIA) are listed at different prices. Nemotron 3 Nano Omni (free) costs less: $0 per 1M input tokens and $0 per 1M output tokens, against $0.06 and $0.24 for Nemotron 3 Nano 30B A3B. Nemotron 3 Nano 30B A3B has the larger context window, 262,144 tokens against 256,000 for Nemotron 3 Nano Omni (free). Only Nemotron 3 Nano 30B A3B supports structured outputs. Nemotron 3 Nano 30B A3B accepts text and produces text; Nemotron 3 Nano Omni (free) accepts text, images, audio and video and produces text.
NVIDIA: Nemotron 3 Nano 30B A3B accepts text and produces text, with support for tools, structured outputs, response formats, and reasoning. NVIDIA: Nemotron 3 Nano Omni (free) also produces text but accepts text, audio, images, and video; their context limits are 262,144 and 256,000 tokens, respectively.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Nemotron 3 Nano 30B A3B | Nemotron 3 Nano Omni (free) |
|---|---|---|
| Maker | NVIDIA | NVIDIA |
| Added to catalog | 14 Dec 2025 | 28 Apr 2026 |
| Input, per 1M tokens | $0.06 | $0 |
| Output, per 1M tokens | $0.24 | $0 |
| Cached input read, per 1M | $0.012 | n/a |
| Context windowTokens | 262,144 | 256,000 |
| Max outputTokens | 235,929 | 65,536 |
| Accepts | text | audio, image, text, video |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | No |
| Reasoning effort control | No | No |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | Nemotron 3 Nano 30B A3B | Nemotron 3 Nano Omni (free) |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0001 | $0 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0017 | $0 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0023 | $0 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0094 | $0 |
Which to choose
Choose Nemotron 3 Nano 30B A3B if
- Cached input costs less: $0.012 against n/a per 1M
- You need the larger context window: 262,144 tokens against 256,000
- You need longer answers in one response: 235,929 tokens against 65,536
- You need answers in a fixed JSON schema
Choose Nemotron 3 Nano Omni (free) if
- Input tokens cost less: $0 against $0.06 per 1M
- Output tokens cost less: $0 against $0.24 per 1M
- It has to read images, audio and video, which the other model does not
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.