Every's Vibe Check: Opus 5.5 Wins Back Codex Converts at ~60% Below Fable's Price
every · x · 2026-09-27
- Team converts return: In Every's review, Mike Taylor and Tyler Nishida—former Claude power users who had switched to Codex—are reconsidering after testing Opus 5.5. Nishida says his "jaw dropped five or six times this week" and he may drop a $200 subscription to afford it.
- New daily driver: Kieran Klaassen finds it as good as or slightly better than Fable 5.1, at roughly 60% below Fable's token price, making it his new default.
- Not a clean sweep: Dan Shipper calls it a "smaller Fable"—faster and cheaper for end-to-end coding—but still prefers Codex/OpenAI models for knowledge work and writing.
- Brand-style test: Asked for a deck in Every's brand style, Opus 5.5 swapped green for black and gave illustrations a fuzzy texture—decisions the team liked, reading as a human designer's personal touch, with consistent illustrations.
- Remaining quirks: Writing is more readable but buries the point, and it can get carried away.
Related event: Opus 5.5 Wins Developers Back from Codex, Early Reviews Say(6 posts)→
More from coding & agent
- DHH on AI coding: thinking "architecture" is your fortress? Models are good at that too — tawnniee · 2026-09-27
- Reverse engineering with coding agents: set it up overnight, wake up to source — moyix · 2026-09-27
- ThePrimeagen joins DHH's Omarchy Core to lead agentic QA with Oligarchy harness — mark_k · 2026-09-27
- LLMs don't write better code — they accelerate the glue work of integrating libraries — markjeffrey · 2026-09-27
- Open-source AI agents now delegate tasks to each other: GrokBot + Muse — Saboo_Shubham_ · 2026-09-27
- 'Agentic AI Killed DevOps' Claim Sparks Developer Pushback — emeka_boris · 2026-09-27