@cognition: As of today, Devin Fusion now incorporates Fable 5. Surprisingly, Fable 5 runs at a lower cost per task than Opus 4.8. …

X AI KOLs Timeline Products
devin-fusion fable-5 ai-coding cost-efficiency model-update

Summary

Devin Fusion now integrates Fable 5, which surprisingly offers lower cost per task than Opus 4.8 due to efficiency improvements in delegation and reasoning.

As of today, Devin Fusion now incorporates Fable 5. Surprisingly, Fable 5 runs at a lower cost per task than Opus 4.8. Even though it’s a more expensive model, we observed cost efficiency improvements in areas like delegation and reasoning chains.
Original Article
View Cached Full Text

Cached at: 07/13/26, 07:59 PM

As of today, Devin Fusion now incorporates Fable 5.

Surprisingly, Fable 5 runs at a lower cost per task than Opus 4.8.

Even though it’s a more expensive model, we observed cost efficiency improvements in areas like delegation and reasoning chains.

Similar Articles

Making Fable Cheaper Than Opus (12 minute read)

TLDR AI

Cognition replaced the Opus model with Fable in Devin's Fusion architecture, achieving higher performance at lower cost despite Fable's higher per-token price, through better delegation and reduced lead model turns.

Devin Fusion (8 minute read)

TLDR AI

Cognition introduces Devin Fusion, a multi-model harness that routes between frontier and cost-effective models using a sidekick architecture, achieving frontier-level performance at 35% lower cost.