Inkling Small vs Inkling: cost comparison
Prices updated 2026-11-01 · computed from live provider data
Short answer: Inkling is cheaper on a
3:1 input/output blend — Free per million tokens versus
Free, a 0% difference.
Both offer the same 1,048,576-token context window, so cost is the deciding factor.
Head to head
| Inkling Small | Inkling | |
|---|---|---|
| Input, per 1M tokens | Free | Free |
| Output, per 1M tokens | Free | Free |
| Blended 3:1, per 1M | Free | Free |
| Context window | 1,048,576 | 1,048,576 |
| Vendor | thinkingmachines | thinkingmachines |
Monthly cost at real volumes
| Workload (input / output) | Inkling Small | Inkling |
|---|---|---|
| 1M in / 250K out | Free | Free |
| 10M in / 2.5M out | Free | Free |
| 100M in / 25M out | Free | Free |
Which should you pick?
Because the context windows are identical, the cheaper option is the better default. Choose Inkling unless you are already standardised on thinkingmachines tooling and want to avoid a second integration.