ALL INTELLIGENCE
OpenRouter (@OpenRouter)T1·Models

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.

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

推文配图