thinkingmachines/inkling vs thinkingmachines/inkling-small
For 100,000 calls of 2,000 in and 500 out, thinkingmachines/inkling-small is cheaper: $150.00 a month at OpenRouter, against $402.50 for thinkingmachines/inkling at Together AI — 2.7× the cost.
Cheapest on each
thinkingmachines/inkling
$402.50/mo
cheapest, at Together AI — $1 in, $4.05 out per million
thinkingmachines/inkling-small
$150.00/mo
cheapest, at OpenRouter — $0.45 in, $1.2 out per million
Aligned facts
Same rows on both sides, including the ones we cannot fill.
| Attribute | thinkingmachines/inkling | thinkingmachines/inkling-small |
|---|---|---|
| Context window | 524K | 524K |
| Accepts | Aa · IMG · AUD | Aa · IMG · AUD |
| Sellers | 3 | 1 |
| Cheapest input rate | $1 / M | $0.45 / M |
| Cached input rate | $0.17 / M | $0.1 / 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 | thinkingmachines/inkling /mo | thinkingmachines/inkling-small /mo |
|---|---|---|
| OpenRouter | $402.502026-10-27 | $150.002026-10-27 |
| Together AI | $402.502026-10-27 | ○ no answer |
| Fireworks AI | $402.502026-10-22 | ○ no answer |
Cheapest tier per seller, this workload only. In and output rates, and a cached prefix, are broken out in the cost calculator.