API Documentation

Authentication and Base URL

Authenticate every request by passing your API key in the Authorization header. The base URL for all endpoints is https://api.notfilter.cc/v1. This structure ensures compatibility with existing OpenAI SDKs without complex configuration changes.

Copycurl https://api.notfilter.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the capital of france"}]
  }'

Your key grants access to the uncensored model. Keep it secure and regenerate it if compromised. The system validates credentials before processing tokens, so invalid keys return errors immediately.

Chat Completions Endpoint

Send text prompts and receive responses via the /v1/chat/completions endpoint. This is your primary interface for interacting with the model. Configure parameters like temperature and top_p to adjust response behavior.

Copyfrom openai import OpenAI

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

The API expects a standard message format. Input text is converted to tokens, processed, and returned as a coherent response. Errors are handled via standard HTTP status codes.

Streaming Responses

Enable real-time output by setting stream: true. The API returns data in chunks as they are generated. This reduces perceived latency for long responses.

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 content. The final chunk includes token usage statistics. Parse these events to display text progressively to your users.

Function Calling and Tools

Define tools to allow the model to call external functions. Specify tool definitions in the request body. The model returns structured arguments when a function call is appropriate.

Copyimport OpenAI from "openai";

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

Execute the function using the returned arguments and pass the result back to the model. This enables complex workflows without manual parsing. Tool choices can be forced or automatic.

JSON Mode

Force structured output by setting response_format to {"type": "json_object"}. This ensures the response is valid JSON. Useful for parsing data in applications.

The model adheres to the schema you provide. Errors in JSON structure are rare but possible. Validate output in your application layer for safety.

Rate Limits and Context Window

Each API key supports 300 requests per minute and 8 concurrent requests. The context window is 100,000 tokens for prompt and completion combined. Max output is 16,000 tokens.

A 401 error indicates an invalid key. A 402 error means you have no prepaid credit. A 429 error signals rate limit exhaustion. Errors are free, so you are not charged for failed requests. Credit never expires.