Uncensored API documentation and quickstart

Authentication and endpoints

Use your API key to access the chat completions endpoint. We provide a single base URL that works with standard SDKs.

• Base URL: https://api.aigatewaypricing.com/v1
• Endpoint: POST /v1/chat/completions
• Models: GET /v1/models returns uncensored

Include your key in the Authorization: Bearer <key> header.

First request

Send a simple message to verify your setup and credit balance.

The model responds to standard prompts without filtering lawful adult content.

Copycurl https://api.aigatewaypricing.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Run a 200k token test on the 70b model"}]
  }'

Check the response status code to confirm success.

Python SDK integration

Use the official openai Python library with our base URL.

Set the API key and model ID to uncensored. The library handles JSON serialization automatically.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.aigatewaypricing.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Import the client and instantiate it with your credentials.

Node SDK setup

Install the openai package for Node.js.

Configure the client to point to our gateway. This allows you to use familiar async/await patterns.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.aigatewaypricing.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Call chat.completions.create with your system prompt and user message.

Streaming responses

Enable streaming by setting stream: true. You receive chunks as they generate.

Token usage statistics appear in the final chunk. This helps you track costs in real-time.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Handle text and usage events in your callback.

Limits, errors and context

You have a 100,000 token context window per request.

Max output is 16,000 tokens. Errors include 401 (invalid key), 402 (no credit), and 429 (rate limit).

You get 300 requests per minute. Refusals for minor sexual content are free.