API

The basics

• Base URL: https://uncensoredchats.com/v1
• Key: make one in your dashboard. Keys start with sk-uc- and go in an Authorization: Bearer header.
• Models: GET /v1/models lists every id with its price. They are also on the models page.
• Endpoints: POST /v1/chat/completions (OpenAI format, streaming and tool calling) and POST /v1/messages (Anthropic format).
• Spend caps: give each key a total or monthly cap in the dashboard. A key that reaches it stops, and your balance is untouched.

curl

curl https://uncensoredchats.com/v1/chat/completions \
  -H "Authorization: Bearer $UNCENSORED_AI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "glm-5.3-xploded",
       "messages": [{"role": "user", "content": "Hello"}]}'

Python

from openai import OpenAI

client = OpenAI(base_url="https://uncensoredchats.com/v1", api_key="sk-uc-...")

reply = client.chat.completions.create(
    model="glm-5.3-xploded",
    messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)

Node

import OpenAI from 'openai';

const client = new OpenAI({ baseURL: 'https://uncensoredchats.com/v1', apiKey: 'sk-uc-...' });

const reply = await client.chat.completions.create({
  model: 'glm-5.3-xploded',
  messages: [{ role: 'user', content: 'Hello' }],
});
console.log(reply.choices[0].message.content);

SillyTavern

Open API Connections from the plug icon, fill these in and press Connect.

API:                     Chat Completion
Chat Completion Source:  Custom (OpenAI-compatible)
Custom Endpoint:         https://uncensoredchats.com/v1
Custom API Key:          sk-uc-...
Model ID:                glm-5.3-xploded

Claude Code and other Anthropic clients

Point the client at the site itself, with no /v1 on the end.

export ANTHROPIC_BASE_URL=https://uncensoredchats.com
export ANTHROPIC_AUTH_TOKEN="sk-uc-..."
export ANTHROPIC_MODEL=glm-5.3-xploded
claude

When a call fails

• 401: the key is missing, mistyped or turned off.
• 402: the balance or the key's cap cannot cover the request. Add credit in Billing or raise the cap.
• 404 model: the id is not one of ours. Copy it from /v1/models.
• 503: the model is busy. Try again in a minute.

Anything else, send it to support with the request id from your dashboard.