Documentation

Image description

Get a text description of an image with a vision model.

Ask a vision model to describe an image — useful for alt text, search tags, moderation, or feeding text into another step in your pipeline. Returns immediately (no job polling).

URL: POST https://api.thefluxtrain.com/api/v1/llm/describe-image

Authentication: x-api-key

Request body

Field	Type	Required	Default	Description
`image_url`	string	Yes	—	`https://...` URL or `data:image/...;base64,...` URI
`prompt`	string	No	—	Custom instruction (generic describe if omitted)
`model`	string	No	`gpt-4o`	Vision-capable OpenAI model

Example

{
  "image_url": "https://example.com/photo.jpg",
  "prompt": "List objects and dominant colors.",
  "model": "gpt-4o"
}

Response

Field	Type	Description
`content`	string	Model-generated description

Example

{
  "data": {
    "content": "A woman in a red coat stands on a rainy city street at night."
  },
  "error": null
}