4o-image-api

The GPT-Image-1 model, also known as ChatGPT 4o Image, is OpenAI’s latest AI image generation model. It understands both text and visual context, allowing developers to create and edit images with remarkable accuracy. Unlike traditional diffusion models, GPT-Image-1 follows instructions precisely, supports consistent styles, and renders legible text — making it ideal for applications in design, marketing, and creative automation.

定价： 每张 8 积分。

在线试跑

表单已按模型规格预填 —— 可直接运行，也可先改任意字段。

可用

表单JSON

提示词

A cozy ceramic coffee mug on a wooden desk by a sunny window, the mug is printed with the word "ModelFold" in clean white letters

Optional text prompt. At least one of prompt or filesUrl is recommended.

files_url

添加图片

Optional reference image list. Supports up to 5 images.

尺寸

1:13:22:3

Aspect ratio of the generated image

余额： —预估预扣8 积分（生成前为预估，完成后显示实际扣除积分）

重置运行

结果

预览JSON

历史下载

该变体的示例输出 —— 点「运行」生成你自己的。

curl https://modelfold.ai/v1/images/generations \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"4o-image-api","prompt":"..."}'