GLM · uncensored

GLM-5.3 Flash Uncensored API pricing

Input / 1M

$0.13

Cached input / 1M

$0.01

Output / 1M

$0.65

USD per million tokens · 128K context · API + CLI · streaming · tools unverified · text input

Designated zero data retention model deployment. API/CLI prompt bodies stay out of our chat-history database. Retention details →

Use this exact model ID

Install the Python openai package and set UNJAILED_API_KEY locally. Keep your real key in your local client or secret manager.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://unjailedai.com/v1",
    api_key=os.environ["UNJAILED_API_KEY"],
)
response = client.chat.completions.create(
    model="glm-5.3-flash-uncensored",
    messages=[{"role": "user", "content": "Say hello in one sentence."}],
    max_tokens=512,
)
print(response.choices[0].message.content)

Connect your tool

Model availability varies. Check live status before a long task. Wallet credit is required; free registration creates no paid subscription.