Images API

Both use the host https://api.fenno.ai and Bearer authentication. Select an image model that supports the specific operation.

Generation parameters

model and prompt select the model and task. Optional size, quality, n, output-format controls and related fields are model-specific. Do not send values copied from a different image family without checking support.

Install openai, set FENNO_API_KEY and FENNO_IMAGE_MODEL:

import os
from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.fenno.ai/v1",
    api_key=os.environ["FENNO_API_KEY"],
    timeout=60.0,
    max_retries=0,
)
 
generated = client.images.generate(
    model=os.environ["FENNO_IMAGE_MODEL"],
    prompt="A lighthouse on a rocky coast, watercolor, no text.",
)
print("Returned images:", len(generated.data))

Edit parameters

Send a supported image file, model and prompt. A mask and other editing options are only meaningful where the selected model supports them; mask dimensions, alpha semantics and file restrictions can differ.

with open("input.png", "rb") as image:
    edited = client.images.edit(
        model=os.environ["FENNO_IMAGE_MODEL"],
        image=image,
        prompt="Keep the subject and replace the background with a beach.",
    )
print("Returned images:", len(edited.data))

Do not manually set a JSON content type for multipart uploads. Let the HTTP client create the boundary.

Response and errors

data[] can contain url or b64_json according to the model and supported response format. Additional usage or revised-prompt fields are not universal. Do not treat a missing URL as failure before checking for base64 output.

For a 400, inspect image format, payload size, dimensions, prompt and optional parameters. A 404 can also indicate an incorrect path or unavailable model; repeated retries do not fix unsupported editing.

See image generation and editing for handling results and error formats.