AI Rate Cardgemma-2b vs Gemma 3 12B IT: API price and specs
Gemma 3 12B IT is 62% cheaper than gemma-2b on input price.
Gemma 3 12B IT is 5% cheaper than gemma-2b on output price.
Gemma 3 12B IT is 52% cheaper than gemma-2b on a 1M-in / 200k-out workload.
| Field | gemma-2b | Gemma 3 12B IT |
|---|---|---|
| Lowest input, per 1M | $0.10 +162.5% | $0.04 |
| Median input, per 1M | $0.10 +99.1% | $0.05275 |
| Lowest output, per 1M | $0.10 +5% | $0.10 |
| Median output, per 1M | $0.10 | $0.15 +42.9% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.13 +110% | $0.06 |
| Context | — | 131K |
| Max output | — | 131K |
| Providers | 2 +86.7% | 15 |
| Regions | — | EU, GLOBAL, US |
| Accepts | — | image, image/gif, image/jpeg, image/png, image/webp, text |
| Returns | — | text |
| Type | Text models | Text models |
| Free option | yes | yes |
| Cheapest provider | aiml | kilo |
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-2b or Gemma 3 12B IT?
Gemma 3 12B IT is 62% cheaper than gemma-2b on input price. Gemma 3 12B IT is 5% cheaper than gemma-2b on output price. Gemma 3 12B IT is 52% cheaper than gemma-2b on a 1M-in / 200k-out workload.
Where can I use both gemma-2b and Gemma 3 12B IT?
aiml, nvidia