qwen-3.8-max vs scaledown/extract
For 100,000 calls of 2,000 in and 500 out, scaledown/extract is cheaper: $8.00 a month at OpenRouter, against $700.00 for qwen-3.8-max at Fireworks AI — 87.5× the cost.
Cheapest on each
qwen-3.8-max
$700.00/mo
cheapest, at Fireworks AI — $2 in, $6 out per million
scaledown/extract
$8.00/mo
cheapest, at OpenRouter — $0.04 in, $0 out per million
Aligned facts
Same rows on both sides, including the ones we cannot fill.
| Attribute | qwen-3.8-max | scaledown/extract |
|---|---|---|
| Context window | ○ no answer | 1M |
| Accepts | ○ no answer | Aa · IMG · FILE |
| Sellers | 1 | 1 |
| Cheapest input rate | $2 / M | $0.04 / M |
| Cached input rate | ○ no answer | ○ no answer |
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 | qwen-3.8-max /mo | scaledown/extract /mo |
|---|---|---|
| Fireworks AI | $700.002026-10-22 | ○ no answer |
| OpenRouter | ○ no answer | $8.002026-10-27 |
Cheapest tier per seller, this workload only. In and output rates, and a cached prefix, are broken out in the cost calculator.