OpenRouter
Catalog quote- Input
- $0.45
- Output
- $1.20
- Cached input
- $0.10
Inkling-Small is a Mixture-of-Experts transformer with 276B total parameters, 12B active, trained on NVIDIA GB300 NVL72 systems. Like Inkling, it features native reasoning over audio and images, variable thinking effort
Scores appear here when an evaluation matches this exact model.
thinkingmachines/inkling-smallthinkingmachines/Inkling-Smallthinkingmachines/Inkling-SmallUpdated Oct 17, 2026
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
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…
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…