Every vibe check: Opus 5.5 matches Fable at ~60% less, wins back Codex users
danshipper · x · 2026-09-23
Every.to's team review of Claude Opus 5.5: near Fable 5.1 capability at roughly 60% less per token and 40% cheaper to run than Opus 5. It dethroned Fable as one engineer's daily driver and pulled ex-Claude power users back from Codex, though it still buries the point in writing and overshoots on simple tasks; Shipper calls it a "smaller Fable"—great for end-to-end coding, less so for knowledge work.
Related event: Claude Opus 5.5 Launches to Top Rankings with Lower Price and Faster Speed(28 posts)→
More from coding & agent
- Anthropic's Opus 5.5 system card: multi-agent runs match single-agent outcomes faster — jyangballin · 2026-09-23
- Stripe demos WebMCP integration: a deep dive through a checkout page's new tools — jeff_weinstein · 2026-09-23
- Building AI agent harnesses that improve across 6 editable control dimensions — MaryamMiradi · 2026-09-23
- Drop launches: rootless Linux sandbox that isolates coding agents at the OS level — aronchick · 2026-09-23
- Splitting Reasoning From Tool Use: Two Lightweight AI Models Screen 30,000 Crystal Candidates in 48 Hours — bravo_abad · 2026-09-23
- Sentry Bets Big on Evals: 1,800 PR-Triggered Runs, 20-50% Token Cost Cuts — zeeg · 2026-09-23