Integrate the Uncensored LLM API

Authentication & Base URL

Use your API key with the base URL https://api.chataiunrestricted.com/v1 for all requests. Generate your key instantly via Google or email on the dashboard, and it appears immediately for copy-paste use.

Include the key in the Authorization header as a bearer token. The endpoint supports standard OpenAI-compatible clients, so you only need to update the base URL and API key in your SDK configuration.

• Keep your key private; one active key replaces the previous one.
• Errors like 401 indicate an invalid key, while 402 signals insufficient credit.

Chat Completions Endpoint

Send a POST request to /v1/chat/completions with the model ID uncensored to receive text responses. The model answers without content refusals for lawful adult use, making it ideal for creative writing and roleplay.

Set the request body with your messages and optional parameters like temperature. Errors and refusals are free, so you only pay for real token usage.

• The model ID is always uncensored.
• No embeddings or image generation are available.

Streaming Responses (SSE)

Enable streaming by setting stream: true to receive token-by-token updates via Server-Sent Events. This reduces perceived latency for interactive applications and allows real-time display of generated text.

The final chunk includes token usage statistics, so you can track consumption accurately. Streaming works with all standard parameters, including temperature and top_p.

• Use streaming for better user experience in chat interfaces.
• Parse the SSE stream to handle partial responses.

Function Calling & Tools

Define tools in your request to enable function calling, allowing the model to return structured data for external use. Use the tool_choice parameter to control whether the model calls a function automatically or manually.

This feature is useful for integrating the API with other services or extracting specific data formats. The model supports standard OpenAI-compatible tool definitions.

• Define tools in the tools array.
• Use tool_choice for precise control.

JSON Mode & Parameters

Set response_format to json_object to enforce JSON output, ensuring consistent parsing for your application. Use parameters like temperature, top_p, and stop to fine-tune the response style.

The context window supports 100,000 tokens for prompt and completion combined, with a max output of 16,000 tokens per request. This allows for extensive context without complex routing.

• Use JSON mode for structured data.
• Adjust parameters for creative control.

Limits, Errors & Context Window

The API enforces a limit of 300 requests per minute per key and 8 concurrent requests. The maximum request body size is 8 MB, ensuring efficient processing for large inputs.

Handle errors like 401 (invalid key), 402 (no credit), and 429 (rate limit) by checking the response status. Credit never expires, and prepaid credit is charged by real token usage.

• Monitor rate limits to avoid 429 errors.
• Top up credit via crypto for continuous use.

cURL

Copycurl https://api.chataiunrestricted.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Run the build script and show errors"}]
  }'

Python

Copyfrom openai import OpenAI

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

Node.js

Copyimport OpenAI from "openai";

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

Streaming

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)