Thinking Machines: Inkling
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...
Everything else
| Max output | — |
|---|---|
| Input / 1M | $1 |
| Output / 1M | $4.05 |
| Cache read / 1M | $0.17 |
| Cache write / 1M | — |
| 1M in + 1M out | $5.05 |
| Takes | text, image, audio |
| Returns | text |
| Tools | yes |
| Reasoning | optional · max, high, medium, low, minimal, none |
| Open weights | yes |
| Released | 2026-07-17 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | thinkingmachines/inkling |
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.