openai/gpt-oss-20b vs openai/o4-mini:batch
For 100,000 calls of 2,000 in and 500 out, openai/gpt-oss-20b is cheaper: $8.10 a month at OpenRouter, against $220.00 for openai/o4-mini:batch at OpenRouter — 27.2× the cost.
Cheapest on each
openai/gpt-oss-20b
$8.10/mo
cheapest, at OpenRouter — $0.018 in, $0.09 out per million
openai/o4-mini:batch
$220.00/mo
cheapest, at OpenRouter — $0.55 in, $2.2 out per million
Aligned facts
Same rows on both sides, including the ones we cannot fill.
| Attribute | openai/gpt-oss-20b | openai/o4-mini:batch |
|---|---|---|
| Context window | 131K | 200K |
| Accepts | Aa | Aa · IMG · FILE |
| Sellers | 1 | 1 |
| Cheapest input rate | $0.018 / M | $0.55 / M |
| Cached input rate | $0.009 / M | $0.1375 / 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 | openai/gpt-oss-20b /mo | openai/o4-mini:batch /mo |
|---|---|---|
| OpenRouter | $8.102026-10-27 | $220.002026-10-27 |
Cheapest tier per seller, this workload only. In and output rates, and a cached prefix, are broken out in the cost calculator.