AI Rate CardGemma 4 31B IT vs Nemotron 3 Nano 30B A3B: API price and specs
Gemma 4 31B IT is 72% cheaper than Nemotron 3 Nano 30B A3B on input price.
Gemma 4 31B IT is 78% cheaper than Nemotron 3 Nano 30B A3B on output price.
Gemma 4 31B IT is 75% cheaper than Nemotron 3 Nano 30B A3B on a 1M-in / 200k-out workload.
Nemotron 3 Nano 30B A3B has a 300% larger context than Gemma 4 31B IT.
| Field | Gemma 4 31B IT | Nemotron 3 Nano 30B A3B |
|---|---|---|
| Lowest input, per 1M | $0.011 | $0.04 +263.6% |
| Median input, per 1M | $0.14 +133.3% | $0.06 |
| Lowest output, per 1M | $0.035 | $0.16 +357.1% |
| Median output, per 1M | $0.40 +66.7% | $0.24 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.018 | $0.072 +300% |
| Context | 262K +75% | 1M |
| Max output | 262K | 262K |
| Providers | 37 | 15 +59.5% |
| Regions | CH, EU, GLOBAL, US | EU, GLOBAL, US |
| Accepts | application/pdf, audio, file, image, image/gif, image/heic, image/heif, image/jpeg, image/png, image/webp, pdf, text, video, video/mp4, video/quicktime, video/webm | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | yes | yes |
| Cheapest provider | inferx | requesty |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
aihubmix, aiml, amazon-bedrock, cortecs, deepinfra, edenai, fastrouter, infomaniak, kilo, novita, ollama-cloud, openrouter, requesty, trustedrouter, vercel
Frequently asked questions
Which is cheaper, Gemma 4 31B IT or Nemotron 3 Nano 30B A3B?
Gemma 4 31B IT is 72% cheaper than Nemotron 3 Nano 30B A3B on input price. Gemma 4 31B IT is 78% cheaper than Nemotron 3 Nano 30B A3B on output price. Gemma 4 31B IT is 75% cheaper than Nemotron 3 Nano 30B A3B on a 1M-in / 200k-out workload.
Which has the larger context, Gemma 4 31B IT or Nemotron 3 Nano 30B A3B?
Gemma 4 31B IT: 262K tokens; Nemotron 3 Nano 30B A3B: 1M tokens.
Where can I use both Gemma 4 31B IT and Nemotron 3 Nano 30B A3B?
aihubmix, aiml, amazon-bedrock, cortecs, deepinfra, edenai, fastrouter, infomaniak, kilo, novita, ollama-cloud, openrouter, requesty, trustedrouter, vercel