Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
21 providers
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
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,...
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,...
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Inklingthinkingmachines/inkling | 1226.0 | 1.04858M | $1.87 | $4.68 | 2026-07-15 | |||
| Thinking Machines: Inkling (free)thinkingmachines/inkling:free | 1226.0 | 1.04858M | Free | Free | — | |||
| Thinking Machines: Inkling (batch)thinkingmachines/inkling:batch | 1226.0 | 524.288K | $1 | $4.05 | — |