Test the workflow,
not the marketing claim.
A useful two-model decision depends on the workload, so this page organizes the evaluation around commercial polish, literal instruction following, layout control, latency, retries, and effective cost per accepted result.
Editorial product photograph of a matte ceramic skincare bottle on pale limestone, soft north-window light, delicate contact shadow, warm neutral palette, 85mm lens compression, no text, no logo.
Running shoe impact
Technical running shoe frozen above a red clay track at impact, fine dust particles suspended in air, directional hard sunlight, visible outsole detail, energetic diagonal composition, commercial sports photography.
Music festival poster
Experimental electronic music festival poster, oversized condensed type placeholders, electric blue field, silver halftone sphere, asymmetric Swiss grid, high contrast screen-print texture, leave all wording blank.
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.
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.