> ## 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 Official Relay Prompt Limit Measured at 8,192 Tokens

> Measured on the official relay for gpt-image-2 and the gpt-image-2.5 family: the effective prompt limit is 8,192 tokens (about 11,000 Chinese characters). Beyond it the provider returns no error and silently ignores the whole prompt, producing an unrelated image. The overview and Long Prompts pages have been updated.

**2026/10/17 00:25 (UTC+8)** · Docs Update · OpenAI

📚 **The effective prompt limit on the GPT-Image official relay is 8,192 tokens; exceeding it raises no error and the whole prompt is silently ignored**

Measured on 2026-10-16 with the official relay for `gpt-image-2` and the `gpt-image-2.5` family: an 8,121-token prompt rendered correctly; from about 8,350 tokens the provider returns no 400 but drops the entire prompt and generates an unrelated image (often a realistic portrait or an interior), with `usage.input_tokens_details.text_tokens` reporting 8. The documented 32,000-character limit is roughly equivalent for English, but Chinese hits the line at about 11,000 characters.

Recommendations:

* Keep Chinese prompts under about 10,000 characters; repeated character sheets and layout rules take the most space, and character appearance can be carried by reference images instead
* If an image has nothing to do with your prompt, check whether that call's `text_tokens` is a single-digit number
* Distill long material with a text model before generating, see [Long Prompts](/en/api-capabilities/image-long-prompt)

The "Prompt limit" row and FAQ in the [GPT-Image 2.5 / 2 overview](/en/api-capabilities/gpt-image-2/overview) have been updated.

***

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


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.