sao10k/llama-3-8b-stheno-v3.2 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 $12.50 for sao10k/llama-3-8b-stheno-v3.2 at Novita AI — 1.6× the cost.
Cheapest on each
sao10k/llama-3-8b-stheno-v3.2
$12.50/mo
cheapest, at Novita AI — $0.05 in, $0.05 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 | sao10k/llama-3-8b-stheno-v3.2 | scaledown/extract |
|---|---|---|
| Context window | ○ no answer | 1M |
| Accepts | ○ no answer | Aa · IMG · FILE |
| Sellers | 1 | 1 |
| Cheapest input rate | $0.05 / 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 | sao10k/llama-3-8b-stheno-v3.2 /mo | scaledown/extract /mo |
|---|---|---|
| Novita AI | $12.502026-10-22 | ○ 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.