thinkingmachines API Pricing
All 6 thinkingmachines models by input price. Refreshed hourly.
| Model | Input /1M | Output /1M | Blended | Context | Intelligence | CPS | |
|---|---|---|---|---|---|---|---|
| Thinking Machines: Inkling Small (batch) | $0.50 | $1.20 | $0.68 | 524K | — | — | Details → |
| Thinking Machines: Inkling | $1.00 | $4.05 | $1.76 | 524K | — | — | Details → |
| Thinking Machines: Inkling (batch) | $1.00 | $4.05 | $1.76 | 524K | — | — | Details → |
| Thinking Machines: Inkling Small (free) | Free | Free | $0.00 | 1.0M | — | — | Details → |
| Thinking Machines: Inkling Small | $0.45 | $1.20 | $0.64 | 524K | — | — | Details → |
| Thinking Machines: Inkling (free) | Free | Free | $0.00 | 1.0M | — | — | Details → |
FAQ
What is the cheapest thinkingmachines model?
By input price, Thinking Machines: Inkling Small (batch) is lowest ($0.50/1M tokens). See the full table above.
How is thinkingmachines priced?
Usage-based: input and output priced separately per 1M tokens, with cache read/write discounts on some models. The Blended column estimates a typical 3:1 request cost.