google/gemini-2.5-flash:batch vs google/gemma-3-4b-it
For 100,000 calls of 2,000 in and 500 out, google/gemma-3-4b-it is cheaper: $15.00 a month at OpenRouter, against $92.50 for google/gemini-2.5-flash:batch at OpenRouter — 6.2× the cost.
Cheapest on each
google/gemini-2.5-flash:batch
$92.50/mo
cheapest, at OpenRouter — $0.15 in, $1.25 out per million
google/gemma-3-4b-it
$15.00/mo
cheapest, at OpenRouter — $0.05 in, $0.1 out per million
Aligned facts
Same rows on both sides, including the ones we cannot fill.
| Attribute | google/gemini-2.5-flash:batch | google/gemma-3-4b-it |
|---|---|---|
| Context window | 1M | 131K |
| Accepts | Aa · IMG · AUD · VID · FILE | Aa · IMG |
| Sellers | 1 | 1 |
| Cheapest input rate | $0.15 / M | $0.05 / M |
| Cached input rate | $0.03 / M | $0.02 / M |
No quality or benchmark row appears here. We hold no throughput or accuracy measurement for either model, and a cost-per-quality figure built from a lab’s own claim would look authoritative and mean nothing.
Cost for this workload — both models, every seller
100,000 calls a month · 2,000 input and 500 output tokens each. Sellers of both models lead, cheapest combined cost first.
| Seller | google/gemini-2.5-flash:batch /mo | google/gemma-3-4b-it /mo |
|---|---|---|
| OpenRouter | $92.502026-10-20 | $15.002026-10-27 |
Cheapest tier per seller, this workload only. In and output rates, and a cached prefix, are broken out in the cost calculator.