Fable 5.1 Cuts Median Response Length by More Than Half
Key Info
Fable 5.1, released Sep 1 and now available on Requesty, responds much more concisely: median output drops from 603 tokens to 270 tokens, signaling a shift toward action over explanation.
Highlights
- Median response length fell from 603 to 270 tokens — a reduction of more than half.
- The model “talks less,” producing fewer explanatory passages and focusing on doing.
- Version 5.1 landed Sep 1 and is available through Requesty.