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.
More from Models
- Yale physicists re-grade AI benchmarks: most are broken, frontier models near saturation — inductionheads · 2026-09-15
- Grok-5 Shipping Soon, Says xAI Isn't Slowing Down as It Chases the Frontier — bindureddy · 2026-09-15
- Podcast: Microsoft researcher hits ~45% on ARC-AGI with tiny recursive networks — ziv_ravid · 2026-09-15
- Users report being routed to GPT-6 Sol, early impressions consistently positive — kimmonismus · 2026-09-15
- Claude Fable 5.1 holds #1: 1M-token input, ties GPT 6 Astra on new benchmarks — DeepLearningAI · 2026-09-15
- AlphaSense tests Fable and Astra as financial researchers: top score but only on par with Opus-5 — CShorten30 · 2026-09-15