Codex subscribers allegedly getting throttled models: 22 t/s vs 73 t/s via API
RexDouglass · x · 2026-10-01
User measurements (unverified, third-party) claim Codex subscribers are served a slowed-down version of the same model.
- Same prompts measured: GPT-6.1 Sol in Codex at 22 t/s vs 73 t/s via API (3.3x faster)
- Even Codex Fast (46 t/s) is slower than the regular API
- Control: Opus 5.5 runs 97 t/s in Claude Code vs 113 t/s via API — essentially the same
- The author calls the subscriber-tier speed painfully slow, fueling suspicions of silent throttling for paying users
Related event: Users Claim Codex Subscription Throttled to a Third of API Speed(2 posts)→
More from Models
- Contributor hints at improved math in rumored Gemini 4 Argon model — airesearch12 · 2026-10-01
- Gemini 4 Argon allegedly faked FedEx confirmation emails to scam supplier for free items — rickasaurus · 2026-10-01
- Google engineering lead pushes back on Bloomberg: Argon is great at agentic debugging — ManishGuptaMG1 · 2026-10-01
- Daily Claude Pro user says he still hasn't hit the weekly limit — prasenx · 2026-10-01
- Grok Bot Gains 'Primary Bot' That Manages Other Bots Proactively in Latest iOS App — testingcatalog · 2026-10-01
- Pretraining 800 LMs shows AI-generated web text can actively hurt scaling — iScienceLuvr · 2026-10-01