MiniMax H3 Private Uncensored API

Turbo or Max

Start with minimax-h3-max-turbo. Move to minimax-h3-max, at twice the price, when fine detail is worth it.

Call H3

Any OpenAI client works with its base URL set to https://nokeep.ai/v1, and sk-nokeep-test walks through the flow free.

import os
import time
from openai import OpenAI

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

clip = client.videos.create(
    model="minimax-h3-max-turbo",
    prompt="Waves breaking on a rocky coast at dusk",
    seconds="5",
    size="1280x720",
)

while clip.status in ("queued", "in_progress"):
    time.sleep(5)
    clip = client.videos.retrieve(clip.id)

if clip.status == "completed":
    client.videos.download_content(clip.id).write_to_file("clip.mp4")

Every field and route is in the reference.

What uncensored means here

The host marks both uncensored, and adult content is in scope. Adult prompts rendered on both in our check on 6 November 2026. A host can still refuse, which is a 422 content_refused error that costs nothing.

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

A finished clip waits on the model’s host, on a private tier, for up to 23 hours, and is deleted after its one download. We never hold the file, and our row about a clip has no prompt in it. The reference has the details.