AI Rate CardGemma 3 12B IT vs Gemma 3 4B IT: API price and specs
Gemma 3 4B IT is 50% cheaper than Gemma 3 12B IT on output price.
Gemma 3 4B IT is 17% cheaper than Gemma 3 12B IT on a 1M-in / 200k-out workload.
| Field | Gemma 3 12B IT | Gemma 3 4B IT |
|---|---|---|
| Lowest input, per 1M | $0.04 | $0.04 |
| Median input, per 1M | $0.05275 +5.5% | $0.05 |
| Lowest output, per 1M | $0.10 +100% | $0.05 |
| Median output, per 1M | $0.15 +50% | $0.10 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.06 +20% | $0.05 |
| Context | 131K | 131K |
| Max output | 131K | 131K |
| Providers | 15 | 11 +26.7% |
| Regions | EU, GLOBAL, US | EU, US |
| Accepts | image, image/gif, image/jpeg, image/png, image/webp, text | image, image/gif, image/jpeg, image/png, image/webp, text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | yes | yes |
| Cheapest provider | kilo | amazon-bedrock |
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, deepinfra, edenai, fastrouter, huggingface, kilo, nvidia, openrouter, trustedrouter
Frequently asked questions
Which is cheaper, Gemma 3 12B IT or Gemma 3 4B IT?
Gemma 3 4B IT is 50% cheaper than Gemma 3 12B IT on output price. Gemma 3 4B IT is 17% cheaper than Gemma 3 12B IT on a 1M-in / 200k-out workload.
Which has the larger context, Gemma 3 12B IT or Gemma 3 4B IT?
Gemma 3 12B IT: 131K tokens; Gemma 3 4B IT: 131K tokens.
Where can I use both Gemma 3 12B IT and Gemma 3 4B IT?
aihubmix, aiml, amazon-bedrock, deepinfra, edenai, fastrouter, huggingface, kilo, nvidia, openrouter, trustedrouter