OpenAI's Fast mode burns 2.5x subscription quota for only 1.5x speedup, tests find
lxfater · x · 2026-10-03
Blogger lxfater tested OpenAI's Fast mode and found output speeds up only 1.5x (about 30 TPS) while token burn roughly doubles.
- Subscription users: Fast consumes quota at 2.5x the standard rate
- Credits or enterprise pay-as-you-go: 2x
- Only GPT-5.6 and GPT-5.5 are officially documented at the 1.5x speedup
The author concludes that trading 2.5x quota for 1.5x speed is a bad deal and suspects OpenAI may deliberately throttle, nudging users into Fast mode to burn tokens faster before placating them with quota resets.
More from Models
- Bittensor's Cascade beats Datadog Toto 2.0 with 84.6% fewer training tokens — bittingthembits · 2026-10-03
- Qwen 3.8 Flash Next q2_0 hits 10 tok/s on a 6GB VRAM laptop via Strata engine — dampflokfreund · 2026-10-03
- Claude Opus 5.5 and Sonnet 5.5 Now Available in Google Antigravity — algo_diver · 2026-10-03
- MIT's VISTA gives Claude visual memory to clear all 25 ARC-AGI-3 games with 57.4% fewer actions — mark_k · 2026-10-03
- Bittensor SN81 generated ~3B tokens in a week, boosting Qwen3-4B math score from 37 to 73 — bittingthembits · 2026-10-03
- Devin called best-value AI subscription: SWE-2 plus Opus 5.5 combo barely uses 10% of quota — CtrlAltDwayne · 2026-10-03