prism-ml/ternary-bonsai-27b vs scaledown/extract
Only scaledown/extract is priced by a seller we read — $8.00 a month at OpenRouter for this workload. Nothing is on record for prism-ml/ternary-bonsai-27b.
Cheapest on each
No priced seller on record.
Every seller we read lists this model at zero, or lists only one half of the pair.
See every model we price →Same rows on both sides, including the ones we cannot fill.
| Attribute | prism-ml/ternary-bonsai-27b | scaledown/extract |
|---|---|---|
| Context window | ○ no answer | 1M |
| Accepts | ○ no answer | Aa · IMG · FILE |
| Sellers | 1 | 1 |
| Cheapest input rate | ○ no answer | $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 | prism-ml/ternary-bonsai-27b /mo | scaledown/extract /mo |
|---|---|---|
| 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.