gpt-4o-image generates image

🌟 Notes for generating images with GPT:

Since the gpt-4o-image endpoint is implemented through technical workarounds and is not an asynchronous interface, it cannot be made completely stable, so instability may occur.Please use the streaming output to view the process in real time.

If you have high stability requirements, it is recommended to use gpt-image-1, whose official API calls are more stable. For the calling method, refer to the official images/generations format; URL details: https://api.cometapi.com/v1/images/generations

Both gpt-4o-image and gpt-image-1 support the chat format, which can be accessed through technical means. URL details: https://api.cometapi.com/v1/chat/completions

curl --location --request POST 'https://api.cometapi.com/v1/chat/completions' \ --header 'Authorization: {{api-key}}' \ --header 'Content-Type: application/json' \ --data-raw '{ "model": "gpt-4o-image", "stream": true, "messages": [ { "role": "user", "content": "Generate a cute kitten sitting on a cloud, cartoon style" } ] }'

{ "id": "chatcmpl-89DrEm9HUEuAk2JUN4tmIi5TEwVam", "object": "chat.completion", "created": 1744696747, "model": "gpt-4o-image", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "```\n{\n \"prompt\": \"A cute kitten sitting on a cloud, in a cartoon style.\",\n \"ratio\": \"1:1\"\n}\n```\n\n>🕐 Queuing.\n\n>⚡ Generating..\n\n>🏃‍ Progress 14...37...61...74..[100](https://videos.openai.com/vg-assets/assets%2Ftask_01jrw0e6vwez5sh16h25kn0xn2%2Fsrc_0.png?st=2025-04-15T04%3A40%3A06Z&se=2025-04-21T05%3A40%3A06Z&sks=b&skt=2025-04-15T04%3A40%3A06Z&ske=2025-04-21T05%3A40%3A06Z&sktid=a48cca56-e6da-484e-a814-9c849652bcb3&skoid=aa5ddad1-c91a-4f0a-9aca-e20682cc8969&skv=2019-02-02&sv=2018-11-09&sr=b&sp=r&spr=https%2Chttp&sig=tVdhsKmI14ibIK%2BKuwhSrCphnrSBZX0d%2FXtqjLVTF08%3D&az=oaivgprodscus)\n\n> ✅ Generation complete\n\n\n![gen_01jrw0e7j2fc2rp7evwe19y0q7](https://filesystem.site/cdn/20250415/CK1wClwp1so6YTPImkPlJpZD8KlrEM.png)" }, "finish_reason": "stop" } ], "data": null, "usage": { "prompt_tokens": 21, "completion_tokens": 373, "total_tokens": 394, "prompt_tokens_details": { "CachedCreationTokens": 0, "text_tokens": 14, "cached_tokens_details": {} }, "completion_tokens_details": {} }, "error": {} }

Request

Responses