Vision

Vision workflows use uploaded image files or hosted assets as model input. Pixapi's current model docs use OpenAI-compatible image edit fields.

Image editing

curl https://api.pixapi.ai/v1/images/edits \
  -H "Authorization: Bearer $PIXAPI_KEY" \
  -F "model=gemini-3-pro-image-preview" \
  -F "prompt=Create a premium social ad using the same product and color palette." \
  -F "image=@product.png" \
  -F "n=1" \
  -F "size=1024x1024"

Input requirements

• Use multipart form uploads for OpenAI-compatible image edit requests.
• Prefer PNG, JPEG, or WebP inputs.
• Keep reference images relevant to the requested output.
• Do not send private user files unless your application has permission to process them.

The older JSON URL-input edit format is available only in Legacy transition format.