Codex usage seems to burn through tokens faster than Claude Code in week-long runs
jdjohnson · x · 2026-07-27
The poster says something may be broken in Codex, or Sol 5.6 is simply too token-hungry and does not match OpenAI's claims. After running Claude Code with several heavy setups for a week, they reached 87% usage before reset; under a similar load in Codex with Sol Medium, Sol High, and one Max thread, they are only at 68% since yesterday's reset.
They note this is the reverse of their previous experience and say OpenAI is usually quick to respond to complaints, but has been quiet despite what looks like a wave of reports that 5.6 usage limits are disappearing faster than expected. Their conclusion is that either users have changed how they operate with 5.5/5.6, or OpenAI is also confused and investigating.
Related event: Users Report Codex Credits Drain Too Fast(2 posts)→
More from coding & agent
- A 9B Ollama agent can run a fully local DJ radio with tools, memory, and TTS — pinku1 · 2026-07-27
- Bugbot rejects an MCP permission flag because it would break path-scoped isolation — zeeg · 2026-07-27
- One GPT-5.6 agent is guarding a Blink security system while another makes a parody rap album — repligate · 2026-07-27
- An agent got unblocked by reusing a logged-in browser, not stealth tricks — armanidev_ · 2026-07-27
- Paper argues graph topology can become the core operating system for AI agents — theomitsa · 2026-07-27
- Claude Code desktop adds UI markup feedback for smoother visual editing — EricBuess · 2026-07-27