AI Rate CardQwen 2.5 72B Instruct vs Gemma 4 12B IT: API price and specs
Gemma 4 12B IT is 95% cheaper than Qwen 2.5 72B Instruct on input price.
Gemma 4 12B IT is 68% cheaper than Qwen 2.5 72B Instruct on output price.
Gemma 4 12B IT is 88% cheaper than Qwen 2.5 72B Instruct on a 1M-in / 200k-out workload.
| Field | Qwen 2.5 72B Instruct | Gemma 4 12B IT |
|---|---|---|
| Lowest input, per 1M | $0.23 +2080.1% | $0.01055 |
| Median input, per 1M | $0.36 +551.3% | $0.05528 |
| Lowest output, per 1M | $0.40 +216% | $0.13 |
| Median output, per 1M | $0.40 +87.5% | $0.21 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.31 +764.2% | $0.03587 |
| Context | 131K | — |
| Max output | 16K | — |
| Providers | 11 | 2 +81.8% |
| Regions | US | — |
| Accepts | text | text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | requesty | trustedrouter |
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, Qwen 2.5 72B Instruct or Gemma 4 12B IT?
Gemma 4 12B IT is 95% cheaper than Qwen 2.5 72B Instruct on input price. Gemma 4 12B IT is 68% cheaper than Qwen 2.5 72B Instruct on output price. Gemma 4 12B IT is 88% cheaper than Qwen 2.5 72B Instruct on a 1M-in / 200k-out workload.
Where can I use both Qwen 2.5 72B Instruct and Gemma 4 12B IT?
siliconflow, trustedrouter