Uncensored API Quickstart Guide

Base URL and Authentication

The API endpoint lives at https://api.gptnofilter.com/v1. Update your client's base URL to this address. Authentication uses a standard API key passed in the Authorization header as a Bearer token. You get one key per account, which replaces any previous key immediately upon generation.

First Request

Send a POST request to /v1/chat/completions. The model ID is uncensored. This endpoint accepts text input and returns text output. It does not support images, audio, or video generation.

Copycurl https://api.gptnofilter.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What are the API limits for this model"}]
  }'

The request body must include the model ID and your message content. The system processes the prompt and returns a completion token.

Python SDK Integration

Use the official OpenAI Python SDK. Point it to our base URL and provide your API key. The code remains identical to standard OpenAI usage, except for the endpoint.

Copyfrom openai import OpenAI

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

This setup allows you to use familiar methods like client.chat.completions.create. The response structure matches the OpenAI standard format.

Node SDK Integration

Install the OpenAI Node.js package. Configure the apiKey and baseURL properties. This ensures compatibility with existing scripts.

Copyimport OpenAI from "openai";

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

Call the completions endpoint with the uncensored model. The SDK handles serialization and header injection automatically.

Streaming and JSON Mode

Enable streaming by setting stream to true. You receive Server-Sent Events (SSE) chunks. The final chunk contains the total token usage. You can also force JSON output using response_format: {type: "json_object"}. This is useful for structured data generation.

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)

Function calling is supported via the tools parameter. The model adheres to the specified tool definitions during execution.

Rate Limits and Context Window

You are allowed 300 requests per minute per key. Concurrency is limited to 8 simultaneous requests. The request body must not exceed 8 MB. The context window is 100,000 tokens total. This includes both the prompt and the completion. Max output is 16,000 tokens per request. If you do not set max_tokens, the limit defaults to 2,048 tokens. Errors and refusals do not consume credit. A 401 error means your key is invalid. A 402 error indicates insufficient credit. A 429 error signals that you hit the rate limit.