Developer Quickstart Guide

Base URL and Authentication

The base URL for our API is HTTPS://api.chatgptunfiltered.com/v1. You must send your API key in the Authorization header as a Bearer token. Our service uses a single model ID named "uncensored" for all requests. You can generate your key via the Get API key page using Google or an email password. No phone number is required, and the key appears immediately upon creation.

• Base URL: HTTPS://api.chatgptunfiltered.com/v1
• Auth Header: Authorization: Bearer YOUR_API_KEY
• Model ID: "uncensored"

Chat Completions Endpoint

Send POST requests to /v1/chat/completions to generate text. The endpoint accepts standard OpenAI-compatible JSON payloads. Our uncensored model processes these inputs and returns raw text without typical content filters. You can adjust parameters like temperature and top_p to control creativity. The response includes token usage statistics for accurate billing.

Errors during processing do not consume your prepaid credit. You only pay for successful token generation.

Copycurl https://api.chatgptunfiltered.com/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?"}]
  }'

Models Endpoint

Use GET /v1/models to verify connectivity and list available models. Our endpoint returns a list containing the single "uncensored" model. This confirms your authentication is correct before you send heavy payloads. The response structure matches the standard OpenAI format for easy compatibility.

You do not need to manage model versions or routing logic. The API serves one dedicated uncensored LLM optimized for unrestricted output.

Copyfrom openai import OpenAI

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

Streaming and SSE Usage

Enable streaming by setting the stream parameter to true. The API returns Server-Sent Events (SSE) for real-time token delivery. This approach reduces perceived latency for long responses. Token usage data appears in the final chunk of the stream. You can parse these events using any standard OpenAI SDK.

Streaming works identically to the standard OpenAI implementation. This ensures your existing code handles our uncensored endpoint without modification.

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)

Parameters and JSON Mode

Support standard parameters like temperature, top_p, stop sequences, and seed. Use response_format with json_object to enforce structured output. Function calling (tools) is fully supported for complex workflows. JSON mode ensures reliable parsing for automated systems.

Our model handles diverse input styles effectively. You can adjust constraints to fit your specific application needs. The API maintains consistency across different parameter combinations.

Error Handling and Limits

Monitor HTTP status codes for integration health. A 401 error indicates an invalid or expired API key. A 402 error means your prepaid credit is exhausted. A 429 error signals you have exceeded the 300 requests per minute limit. The context window supports 100,000 tokens total. Output is limited only by the room left in the window per request. Request bodies cannot exceed 8 MB.

Errors do not consume your credit. Retry logic should handle 429s with exponential backoff. Check your balance regularly to avoid service interruption.

Node.js

Copyimport OpenAI from "openai";

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