Images

The Images resource gives you text-to-image generation, billed in DA per output image. It works with the OpenAI SDK's images.generate helper, which maps to POST /v1/images/generations.

Generate an image#

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/api/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.images.generate(
    model="google/gemini-2.5-flash-image",
    prompt="An aerial view of Algiers at dusk, impressionist oil painting style.",
    n=1,
    size="1024x1024",
)
print(resp.data[0].url)

The response data[].url is a signed, time-limited URL to the stored image (not raw base64). If the provider returns no image, the call fails with 502 no_image and you are not charged.

Editing and variations (images.edit, images.create_variation) are not yet supported — only generation is live.

Pricing#

Image generation is billed per output image — n images cost n × the model's per-image rate. Rates are shown in the model catalog. See the image API reference.