Uncensored Qwen3.8 27B API

Base URL https://api.unrestricted.sh/v1, model id qwen3.8-27b-uncensored. Any OpenAI-compatible SDK works, and so does the Anthropic messages endpoint.

curl https://api.unrestricted.sh/v1/chat/completions \
  -H "Authorization: Bearer $UNRESTRICTED_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.8-27b-uncensored",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.unrestricted.sh/v1",
    api_key=os.environ["UNRESTRICTED_API_KEY"],
)

resp = client.chat.completions.create(
    model="qwen3.8-27b-uncensored",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

API reference

One command sets up OpenCode, Codex CLI, Qwen Code, Goose, OpenHands, Continue, Crush or Pi. Then pick Qwen3.8 27B Uncensored from the model list.

sh -c "$(curl -fsSL https://unrestricted.sh/setup.sh)"

Step-by-step guides: OpenCode, Codex CLI, Qwen Code, Goose, OpenHands, Continue, Crush, Pi, Aider, Cline, Roo Code, Kilo Code, Zed.

Context window

262,144 tokens

Input

$1.00 per million tokens

Cached input

$0.10 per million tokens

Output

$2.00 per million tokens

Cached-input pricing applies to the API and coding tools; messages in the web chat pay the full input price.

Runs on our own GPU servers. Zero data retention: prompts and replies are never stored.