Skip to main content

​
What you will build

You will call POST /v1/images/generations, generate one image with a GPT image model, decode the returned b64_json, and save it as an image file.

​
Prerequisites

  • A CometAPI API key stored in COMETAPI_KEY
  • Python 3.10+ or Node.js 18+ for file-saving examples
  • A server-side environment. Do not call image generation from public frontend code with a secret key.

​
API key, base URL, authentication

Use the OpenAI-compatible image endpoint: 
https://api.cometapi.com/v1/images/generations
Authenticate with a Bearer token: 
Authorization: Bearer $COMETAPI_KEY

​
Code examples

Use the tabs below for copyable examples in cURL, Python, and Node.js. 
curl https://api.cometapi.com/v1/images/generations \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A paper boat floating on calm water at sunrise.",
    "quality": "low",
    "size": "1024x1024",
    "output_format": "jpeg"
  }'

​
Flow explanation

GPT image generation returns the completed response in one request. GPT image models return base64 image data in data[0].b64_json. Decode that value and write the bytes to a file that matches output_format. If you need URL output, check whether the selected model supports URL responses. GPT image models use base64 output in the maintained reference example.

​
Common parameters

ParameterUse
modelGPT image model ID. The reference example uses gpt-image-2.
promptText description of the image to generate.
sizeRequested output size. Supported values depend on the selected model.
qualityQuality setting for models that support it.
output_formatEncoded image type for GPT image results, such as jpeg, png, or webp.

​
Troubleshooting / FAQ

Confirm you decoded b64_json as base64 bytes and saved the file extension that matches output_format.
Image parameters vary by model. Start with the minimal reference example, then add one optional field at a time.
Use b64_json for GPT image models. URL output is model-specific.

​
Next steps