Images API

The image API allows you to generate one or several images from a natural language prompt. Depending on the selected provider and model, you can adjust parameters such as size, quality and aspect ratio.

Check the Globant Enterprise AI API Reference for generic variables needed to use the API.

Endpoint

POST /images

Generates images from a text description using a selected model and rendering settings.

Request

• Method: POST
• Path: $BASE_URL/image
• Headers:
  Content-Type: application/json
  Authorization: Bearer $SAIA_APITOKEN

Request Body

{
  "model": "string",         // e.g. "openai/gpt-image-1"
  "prompt": "string",        // Description of the desired image
  "n": integer,              // Number of images to generate (1-10 depending on model)
  "quality": "string",       // Rendering quality, e.g. "high"
  "size": "string",          // Image dimensions, e.g. "1024x1024" (allowed values: 1024x1024, 1024x1536 or 1536x1024).
  "aspect_ratio": "string"   // Relationship between an image’s width and height (1:1, 9:16, 16:9, 3:4, 4:3). Optional.
}

Supported models and their accepted parameters are listed in the following table.

cURL Sample

curl -X POST "$BASE_URL/images" \
-H 'Authorization: Bearer $SAIA_APITOKEN' \
-H 'Content-Type: application/json' \
-d '{
  "model": "openai/gpt-image-1",
  "prompt": "generate a lovely bath basket with attractive items in it",
  "n": 1,
  "quality": "high",
  "size": "1024x1024"
}'

See Also

OpenAI
Google Vertex AI
xAI

Availability

Since March 2025 release.