NoFilter AI API Documentation

Authentication and Setup

Access the NoFilter AI API by updating your client's base URL to https://api.nofilterai.cc/v1. You need an API key, which you generate instantly by signing up via Google or email on the Get API key page. The key is shown immediately after creation. Use this key in the Authorization header as a Bearer token for all requests. No phone number or credit card is required for the trial, though top-ups use crypto. Keep your key secure; it provides the only access to your prepaid credit.

When you sign up, you receive $0.50 in trial credit valid for 7 days. This is sufficient to test the endpoint and verify integration before committing to a larger crypto top-up. The API key is unique to your account, and generating a new one replaces the previous active key.

Your First Request

Send a standard OpenAI-compatible request to POST /v1/chat/completions. Set the model field to uncensored. This model is an open-weight LLM optimized to answer without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor's model. The endpoint accepts text in and returns text out. You can test the integration with a simple prompt to verify the uncensored behavior.

The request body must include messages with a role and content. The system will process the input and return a response token. If you encounter a 401 error, your key is invalid. A 402 error indicates insufficient credit. Use the following example to initialize your first call.

Copycurl https://api.nofilterai.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Python SDK Integration

Use the official OpenAI Python SDK to interact with the NoFilter AI API. Configure the client with the base URL and your API key. The uncensored model ID is the only valid model for this endpoint. This approach lets you drop in the SDK and start generating content immediately. The SDK handles serialization and retries automatically.

Set the temperature and top_p parameters to control randomness. The response object provides access to the generated text and token usage. This method is ideal for backend services or scripts where synchronous calls are preferred. Ensure you handle potential exceptions for rate limits or insufficient funds.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.nofilterai.cc/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 SDK Integration

For JavaScript developers, the OpenAI Node SDK works seamlessly with our uncensored API. Point the client to https://api.nofilterai.cc/v1 and pass your API key. The uncensored model supports standard chat completions. This setup is perfect for web servers or edge functions that need to generate text on demand.

Handle the response data to extract the assistant's message. The SDK manages the HTTP connection, so you can focus on the application logic. Token usage is included in the response object, allowing you to track costs accurately. This integration maintains the same OpenAI-compatible structure, ensuring minimal code changes if you switch contexts.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.nofilterai.cc/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

Enable streaming by setting stream to true in your request. The API returns data as Server-Sent Events (SSE). Each chunk contains a portion of the response, allowing you to display text in real-time. Token usage information is provided in the final chunk, which signals the end of the stream.

Streaming is useful for chat interfaces or live displays. Handle the SSE events to accumulate the complete response. This method reduces perceived latency for end-users. Ensure your client can parse partial JSON objects or text deltas correctly. The streaming response maintains the same model behavior and uncensored capabilities.

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, Errors, and Context

Your API key is limited to 300 requests per minute and 8 concurrent requests. The request body must not exceed 8 MB. The context window is 64,000 tokens total, with a max output of 16,000 tokens (or 2,048 if max_tokens is unset). Errors include 401 for invalid keys, 402 for no credit, and 429 for rate limits. Credit is charged by real token usage; errors are free. Prepaid credit never expires. Use these constraints to design your application's retry logic and queueing system.