Skip to main content
2026/10/4 00:15 (UTC+8) · Model Status · OpenAI ⚠️ gpt-image-2.5-sunburst-vip and gpt-image-2.5-flare-vip have been unstable lately due to occasional capacity shortages Both models run on the official-reverse route, and their supply depends on provider-side risk controls and account capacity, so capacity sometimes runs short for a while and requests fail. We are doing our best to keep capacity healthy; to keep your workflow from stalling, add client-side retries on failure or rotate across several models. If you need other options, the following models are available — pick whichever fits:
  • gpt-image-2-vip: also official-reverse, $0.03 per image, currently more stable than the 2.5 series
  • Official gpt-image-2.5-sunburst: stable, supports 2K / 4K; billed per token, so higher resolutions and higher quality levels cost more per image
  • gpt-image-2.5-all: native image generation from ChatGPT web, high quality and fast, $0.03 per image; outputs 1K only, no 2K / 4K
Note: APIYI passes image results through transparently and does no secondary upscaling — gpt-image-2.5-all returns the native 1K image. For parameters and setup, see the GPT-Image-2-VIP overview, the GPT-Image 2.5 official overview and the GPT-Image-2.5-All overview. Thanks for your understanding — we keep operating around the clock.
← Back to Live Updates · 📚 Monthly archive