NoFilter API Documentation

Authentication and Base URL

Start by registering at Get API key. No credit card is required to receive $0.50 in trial credit, valid for 7 days. Your API key is displayed immediately after signup. You can regenerate it at any time, which instantly revokes the old key.

The base URL for all requests is https://api.nofilterapi.com/v1. This endpoint is compatible with official OpenAI SDKs and any standard OpenAI-compatible client. Update your client configuration to point to this base URL and inject your key into the Authorization header as a Bearer token.

First Request

Send a standard chat completion request to generate text. The model ID is always uncensored. The API accepts text input and returns text output without content refusals for lawful adult, fictional, or controversial topics.

• Context window: 64,000 tokens (combined prompt and completion).
• Hard limit: sexual content involving minors is blocked.

Use this cURL command to test your key:

Copycurl https://api.nofilterapi.com/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

For Python developers, configure the official openai library to use our base URL. This ensures compatibility with the standard request-response cycle for text generation.

• Set base_url to https://api.nofilterapi.com/v1.
• Provide your API key via the api_key parameter.

Install the SDK via pip and initialize the client to start generating text.

Copyfrom openai import OpenAI

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

Node.js developers can achieve the same result by configuring the OpenAI client instance. Pass the base URL and API key to ensure requests route correctly to our uncensored model.

• Use new OpenAI({ baseURL: 'https://api.nofilterapi.com/v1', apiKey: 'YOUR_KEY' }).
• Call chat.completions.create with model uncensored.

This setup works for both synchronous calls and streaming, provided you configure the stream flag appropriately.

Copyimport OpenAI from "openai";

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

To receive text token-by-token, enable streaming in your request payload. This is required for real-time output; it is not the default behavior.

• Set stream: true in the request body.
• Parse Server-Sent Events (SSE) from the response.

Streaming works with both the cURL, Python, and Node clients when the flag is explicitly set. This is ideal for chat interfaces where you want to display text as it is generated.

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

Monitor these limits to avoid service interruptions:

• Rate Limit: 300 requests per minute per key. Exceeding this returns a 429 error.
• Request Size: Maximum body size is 8 MB.
• Context Window: 64,000 tokens total. If you exceed this, the model will truncate older content.

Common errors include 401 for invalid keys, 402 if you have insufficient prepaid credit, and 429 for rate limits. All pricing is usage-based; prepaid credit never expires.