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,...
24 providers
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
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,...
Efficient on-device Gemma 3n model for text, image, and audio understanding
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Thinking Machines: Inklingthinkingmachines/inkling | 52.1 | 524.288K | $1 | $4.05 | 2026-07-15 | |||
| Gemma 3n E4B ITgoogle/gemma-3n-e4b-it | 3.2 | 32.768K | — | — | 2025-06-26 |