Test the workflow,
not the marketing claim.
A successful HTTP response does not guarantee a usable asset, so this checklist combines machine-readable file checks with task-specific visual acceptance rules and stores rejection reasons for later model and prompt analysis.
Over-ear headphones isolated as a clean ecommerce cutout, transparent background, accurate soft edge detail around fabric ear pads, neutral product color, no floor, no text, no added accessories.
Exploded running shoe
Exploded technical view of a running shoe with upper, laces, foam midsole, plate and outsole separated vertically, clean off-white background, precise alignment, soft studio shadows, no labels.
Forest ranger character sheet
Character sheet for Mara, a forest ranger with cropped auburn hair, olive field jacket, brass compass and worn canvas backpack; front, profile and three-quarter views; neutral studio background; consistent facial features.
Climate intelligence dashboard
Editorial analytics dashboard for a climate intelligence product, dense but legible information hierarchy, off-white canvas, dark graphite type, acid green data accents, modular card grid, desktop viewport.
PYTHON QUICKSTART
Keep the request reproducible.
Store credentials in the environment. Record the exact model identifier, dimensions, test date, and retry count with the resulting asset.
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["APIMART_API_KEY"],
base_url="https://api.apimart.ai/v1",
)
result = client.images.generate(
model="gpt-image-1-official",
prompt=PROMPT,
size="1024x1024",
n=1,
)Before you publish a result
- Record model ID, parameters, date, latency, and retry count.
- Review instruction following and protected attributes.
- Flag invented text, marks, anatomy, or unwanted objects.
- Keep the raw output linked to the original fixture.
- Do not claim a universal winner from one prompt.