Chat Completions API Documentation

Authentication and base URL

Connect by setting your API key and base URL in your client. The base URL is https://api.uncensoredlocal.com/v1. Every request requires the Authorization header with your key. No phone number is needed for signup, and you can authenticate via Google or email. Errors and refusals do not consume credit, so testing is free.

First request

Send a standard completion to generate text. Use the model ID uncensored for the model. The API accepts text input and returns text output. You can test the connection immediately after generating your key.

Copycurl https://api.uncensoredlocal.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Find the current UTC timestamp."}]
  }'

This returns the generated text in the response body. You can adjust parameters like temperature to control creativity. The model is tuned to answer without content refusals for lawful adult use.

Python SDK

Use the official OpenAI Python library to integrate quickly. Set the base URL to point to our service. Initialize the client with your API key and send a chat completion request.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.uncensoredlocal.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)

The response object contains the generated content. You can access the text directly from the message object. This works with any standard OpenAI-compatible client library.

Node SDK

Install the OpenAI Node package to start building. Configure the base URL and API key in the client instance. Send a request to the chat completions endpoint.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uncensoredlocal.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);

The result provides the full completion details. You can parse the text and use it in your application. The API supports all standard parameters for fine-tuning the output.

Streaming responses with SSE

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) as tokens are generated. This allows for real-time display of the output to the user.

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)

Each chunk contains partial text. The final chunk includes the token usage statistics. Streaming reduces the perceived latency for long responses. You can handle errors during the stream event by event.

Rate limits and quotas

Each API key is limited to 300 requests per minute. You can have 8 concurrent requests at the same time. The request body must not exceed 8 MB. If you send a request with an invalid key, you receive a 401 error. A 402 error indicates no credit. A 429 error means you hit the rate limit. The context window is 100,000 tokens for prompt and completion together. Max output is 16,000 tokens per request. Errors are free, so you can test limits without cost.