Thinking Machines: Inkling
thinkingmachines/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,...
Modalities
TextImageAudio
In / out price
₩1,755 / ₩7,108
1M
Context
1.05M
Released
Jul 18, 2026
Providers
Several places host the same model. Requests are spread by priority and health, and a local GPU always goes first when one is available.
| Provider | Context | Quantization | Max output | Priority | State |
|---|---|---|---|---|---|
| OpenRouter | 1.05M | — | — | 50 | unknown |