AI Rate CardGemma 4 vs nemotron-3-nano: API price and specs
nemotron-3-nano is 57% cheaper than Gemma 4 on input price.
nemotron-3-nano is 40% cheaper than Gemma 4 on output price.
nemotron-3-nano is 51% cheaper than Gemma 4 on a 1M-in / 200k-out workload.
| Field | Gemma 4 | nemotron-3-nano |
|---|---|---|
| Lowest input, per 1M | $0.14 +133.3% | $0.06 |
| Median input, per 1M | $0.16 +166.7% | $0.06 |
| Lowest output, per 1M | $0.40 +66.7% | $0.24 |
| Median output, per 1M | $0.45 +87.5% | $0.24 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.22 +103.7% | $0.11 |
| Context | 256K | — |
| Max output | — | — |
| Providers | 4 | 2 +50% |
| Regions | EU | — |
| Accepts | image, text | — |
| Returns | text | — |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | ollama-cloud | ollama-cloud |
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
Frequently asked questions
Which is cheaper, Gemma 4 or nemotron-3-nano?
nemotron-3-nano is 57% cheaper than Gemma 4 on input price. nemotron-3-nano is 40% cheaper than Gemma 4 on output price. nemotron-3-nano is 51% cheaper than Gemma 4 on a 1M-in / 200k-out workload.
Where can I use both Gemma 4 and nemotron-3-nano?
ollama, ollama-cloud