Thinking Machines' Inkling model hits OpenRouter
Thinking Machines Lab has made their new open-weights Mixture-of-Experts (MoE) model, Inkling, available on OpenRouter. The model features 975 billion total and 41 billion active parameters, supports a 1 million token context window, and provides controllable reasoning across text, images, and audio.
Immediate API availability for a 975B parameter open model lowers the barrier to entry significantly.
* Large scale, efficient activation: The MoE architecture allows 41B active parameters to run efficiently while leveraging a 975B parameter capacity.
* True multimodality: Integrated text, image, and audio support combined with a massive 1M context window makes it highly competitive.
* Lower setup friction: Hosting a model of this scale is out of reach for most developers, making API access on OpenRouter crucial for widespread testing.
DISCOVERED
1h ago
2026-07-17
PUBLISHED
2h ago
2026-07-17
RELEVANCE
AUTHOR
OpenRouter
