> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apiyi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# gpt-image-2-all Speed Restored, Temporary Redirect Reverted

> gpt-image-2-all speed is back to normal, and the 7/13 temporary redirect to gpt-image-2-vip has been reverted. The two models run on separate routes (ChatGPT vs Codex) and remain split by model: gpt-image-2-all is faster, while gpt-image-2-vip currently supports the size parameter.

**2026/7/14 09:28 (UTC+8)** · Model Status · OpenAI

✅ **`gpt-image-2-all` speed is back to normal — the temporary redirect has been reverted and the original route restored**

After monitoring, `gpt-image-2-all` speed has recovered, and the 7/13 safeguard that temporarily pointed it to `gpt-image-2-vip` has been changed back. The two models run on two separate underlying routes — `gpt-image-2-all` on ChatGPT and `gpt-image-2-vip` on Codex — so they remain split by model.

Each route has its own characteristics (pick as needed):

* `gpt-image-2-all`: faster image generation
* `gpt-image-2-vip`: currently supports the `size` parameter (on this reverse-engineered route the capability carries no guarantee of permanent availability)

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

***

← [Back to Live Updates](/en/live) · 📚 [Monthly Archive](/en/live/archive)