Z-Image Turbo Private Uncensored API

What it’s good at

• Speed. About 3 to 4 seconds a picture in our checks on 6 November 2026.
• Photographic pictures. It suits products, scenes and people.
• Long prompts. It reads up to 7,500 characters.

Call Z-Image Turbo

The model id is z-image-turbo. Any OpenAI client works with its base URL set to https://nokeep.ai/v1, and sk-nokeep-test tries the request free.

import base64
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://nokeep.ai/v1",
    api_key=os.environ["NOKEEP_API_KEY"],
)

result = client.images.generate(
    model="z-image-turbo",
    prompt="A lighthouse on a rocky coast at dusk, photograph",
    size="1024x1024",
)

with open("picture.webp", "wb") as f:
    f.write(base64.b64decode(result.data[0].b64_json))

Every field is in the reference.

What uncensored means here

This is the one image model here the host doesn’t mark uncensored. Our blur is off and nothing was flagged in our check on 6 November 2026, but it held back more on an adult prompt than the others, so explicit requests can come back softer. For those, use chroma.

Four hard limits stay: sexual content involving minors, sexual content of real people, mass-casualty harm and targeting a real person. A prompt that crosses one gets 422 hard_limit and costs nothing.

What private means here

The picture comes back as base64 in the response, not as a link to a stored file. The model runs on a private tier that stores no prompts or results. We keep one row of counts for billing. What we keep has the details.