API documentation for uncensored models

Authentication and base URL

Send requests to our base URL with your API key in the Authorization header to access the uncensored model immediately.

Use Bearer <your-key> for every call. The key is generated when you sign up via Google or email. Keep it secure, as it identifies your prepaid account.

We use standard OpenAI-compatible authentication. If your key is invalid, you receive a 401 error. If your credit is depleted, you receive a 402 error requiring a crypto top-up.

First request

Make your first request by posting a simple message to the chat completions endpoint with your API key.

This cURL example demonstrates the minimal structure required to get a text response from the uncensored model.

Replace <YOUR_API_KEY> with the key shown on your dashboard. The response contains the generated text in the content field.

Copycurl https://api.chatgptnofilter.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list 3 unix commands to find large files"}]
  }'

Python integration

Use the official OpenAI Python library to interact with our API by pointing it to our base URL.

This approach requires no custom client logic. Simply set the base_url and provide your API key. The library handles serialization and response parsing automatically.

This method works seamlessly with existing codebases that target OpenAI. You only need to adjust the endpoint configuration.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.chatgptnofilter.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 integration

Integrate with the API in Node.js by initializing the client with our specific base URL and credentials.

The Node SDK mirrors the Python client structure. Pass the base URL and API key during initialization. The rest of the code remains identical to standard OpenAI implementations.

This allows you to swap providers without rewriting your application logic. The response structure matches the OpenAI specification.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.chatgptnofilter.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 responses

Receive text token-by-token by setting stream: true in your request parameters.

Streaming reduces perceived latency for long outputs. Each chunk contains a partial response. The final chunk includes the token usage statistics for billing.

Handle the stream events in your code to update the UI in real time. This is essential for chat interfaces where users expect immediate feedback.

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)

Limits and context window

The model supports a 100,000 token context window for combined input and output.

Rate limits are set to 300 requests per minute and 8 concurrent requests per key. Request bodies must not exceed 8 MB.

If you exceed the rate limit, you receive a 429 error. Wait a few seconds before retrying. The context window allows for extensive conversation history without immediate truncation.