gpt-image-2-all Compute Restored — About 40s per Image at Best

2026/7/15 16:19 (UTC+8) · Model Status · OpenAI ✅ gpt-image-2-all speed is back to normal — fast cases complete in about 40 seconds The ChatGPT website has recovered its compute capacity, and this reverse-engineered model’s speed has returned to normal with it — our call logs show first-byte times mostly in the 30-60 second range, with fast cases finishing around 40 seconds (screenshot below). Send traffic with confidence: no RPM cap to worry about, and supply is ample.

gpt-image-2-all call log screenshot with first-byte times concentrated in the 30-60 second range

Thanks for your patience — we keep operating and maintaining the service.

← Back to Live Updates · 📚 Monthly Archive