Tests show OpenAI hasn't changed Codex quotas: 800M+ Astra tokens per cycle

daniel_mac8 · x · 2026-09-15

An analysis of two Codex 20x accounts on the author's main dev system found that OpenAI hasn't changed anything for Astra usage in Codex since launch: consumption runs north of 800M tokens per reset cycle, overwhelmingly cached input. Minor variance comes from Luna tokens (per-model breakdown in comments) and light use elsewhere. A concrete accounting directly relevant to paying subscribers wondering what their quota really buys.

Original post →

More from Models

Models channel →