OpenRouter Adds Inkling, a Large Open-Weights Multimodal Model
OpenRouter now offers Inkling, a large open-weights multimodal model with 1M context.
@OpenRouter7 hours ago
TL;DR:
- Inkling has 975B total parameters, 41B active parameters, and 1M-token context.
- It gives developers access to an open multimodal model for text, images, and audio.
- Users can test it alongside closed and other open models on the same platform.
- Real tests on quality, speed, cost, and reliability will show how useful it is.
Headline
OpenRouter now includes Thinking Machines' Inkling, an open-weights multimodal model with 1M-token context.
Summary
Inkling is available on OpenRouter. It's a mixture-of-experts model with 975B total parameters, 41B active parameters, 1M context length, and support for text, images, and audio.
Analysis
The model uses sparse activation for efficiency. Open weights, long context, and multimodality suit agent workflows and document-heavy tasks. On OpenRouter it is easy to compare against other models. The real test is how it performs on actual tasks versus closed models.
Impact Assessment
Significance: High Categories: Model Release, Open Source, Developer Tools