OpenRouter Fixes Crouton Alpha Bug That Halted Agents Mid-Task
Original title: Update on Crouton Alpha 🥐
38AI Score
OpenRouter fixed a bug in its stealth reasoning model Crouton Alpha that caused agents to stop early, typically right before a tool call; agents should now run tasks to completion. The model was previously announced as free to use with a 1M-token context, text/image/audio/video input, and no training on user data.
Related Entities
Full Report
OpenRouter · 2026-11-05 19
Update on Crouton Alpha 🥐
We squashed a bug that could make it stop early mid-task, usually right before a tool call. Agents should now run all the way through.
Give it another spin and let us know how it feels: https://openrouter.ai/stealth/crouton-alpha
↳ 引用 @OpenRouter (OpenRouter): 🥷 New stealth model: Crouton Alpha
A highly efficient reasoning model built to scale out the work your agents repeat all day.
- Free to use
- 1M token context
- Text, image, audio, and video input
- No training on data
