gpt-image-2-vip supports 4K output and the quality parameter again
gpt-image-2-vip runs on a reverse-engineered route, so its capabilities fluctuate with OpenAI’s rule changes: 4K output and quality were unavailable for a period, and both are working again as of this update; size has stayed in effect since the 7/11 update. A reverse-engineered route carries no permanent availability guarantee — a future rule change upstream may break it again.
What is supported right now:
- Image generation:
/v1/images/generations - Image editing:
/v1/images/edits - Model name:
gpt-image-2-vip - Size: common 1K / 2K / 4K sizes
- Quality:
qualityacceptslow/medium/high - Billing: per-request, $0.03 per call
gpt-image-2-vip, please use a Default group per-request billing token.
Thanks for following along — we keep tracking upstream changes.
📖 Onboarding: gpt-image-2-vip Overview
← Back to Live Updates · 📚 Monthly Archive