API
GPT-4o Image Generation
Interface Description
As OpenAI has yet to officially release a GPT-4 image generation API, we’ve temporarily made two reverse-engineered endpoints—gpt-4o-image
and gpt-4o-image-vip
—available, enabling users to preview GPT-4o’s powerful image creation capabilities.
Please note, these reverse-engineered endpoints do not guarantee consistent stability and are intended solely for early access and exploratory use.
Once OpenAI officially launches the GPT-4 image API, we will immediately discontinue these unofficial endpoints and seamlessly transition to the official stable release.
Notes
- Special Note: Regardless of the cause, once the API call is initiated, charges will apply even if the generation fails.
- The name of living artists (such as “Ghibli” and “Makoto Shinkai”) will trigger
input_moderation
error, causing generation failure. You can avoid this by using non-sensitive words like “Ghibli” and “Bright Modern Japanese Anime Style”. - In general, “style” is safer than “artist”, like “Pixar” is also supported.
- A more secure approach is to use the name of deceased artists or corresponding styles, such as “Van Gogh” and “Mona Lisa”.
Model and Pricing
Model | Price ($/IMG) |
---|---|
gpt-4o-image-vip | $0.007 |
gpt-4o-image | $0.003 |
Python Example
Using the familiar v1/completions
endpoint, we provide support, which is fully compatible. For specific usage, please refer to:
Output Example
Effect Demonstration
Girl with a Pearl Earring
- The famous painting is reinterpreted, with text and watermark directly output.

Pixar
- The Pixar 3D Cartoon style, stable as ever.

Ghibli
- The most popular Ghibli
Practical Tips
- Support any language, Chinese drawing is also stable, but we don’t recommend drawing a large amount of text.
- Specify the aspect ratio in the prompt, otherwise 4o will automatically determine it. Supports 2:3, 3:2, 1:1.
- Give reference images if you don’t have inspiration, support single image and multi-image.
- Upload images can be compressed for pre-processing, improve speed.
- Support transparent background, no need to remove the background.——just add the requirement in the prompt.