Dev claims Codex is 10x less token-efficient than Claude Code: $20 buys one day vs one week
DimitrisPapail · x · 2026-09-25
Developer Dimitris Papail called out OpenAI Codex's token efficiency, claiming it is still roughly 10x less efficient than Claude Code.
- At the $20 tier, he says you get about one day of astra usage on Codex vs one week of Fable on Claude Code.
- He expresses disappointment that the Pro plan's quota only lasts about a day of use.
- A first-hand usage/pricing comparison relevant to developers choosing between the two coding subscriptions.
Related event: Users Slam OpenAI Codex for Poor Token Efficiency and Fast Quota Burn(2 posts)→
More from coding & agent
- Dev builds AgentCam MCP server to feed camera angles to Opus 5.5 for agentic CAD — _Stocko_ · 2026-09-25
- AEWM: editing agent task states beats simulating tool responses — RUC · 2026-09-25
- Qwen-Planner-Agent: a closed-loop AI-for-AI framework for mobile planner agents — Tongyi-MAI · 2026-09-25
- Claude Code ships experimental advisor tool to consult a stronger model at key moments — anshulkundaje · 2026-09-25
- NeurIPS 26 paper accepted; workshop organizers ask what agent behaviors lie beyond planning and reasoning — DanielKhashabi · 2026-09-25
- Building an Obsidian carousel editor with just Claude Code, skills and markdown files — evielync · 2026-09-25