How do I know my API key is valid?

Send a simple request to the chat completions endpoint. If you receive a 401 error, the key is invalid or expired. A successful response confirms authentication.

What happens if I run out of credit?

The API returns a 402 error indicating insufficient funds. Your credit does not expire, so you can top up anytime via crypto. No subscription is lost.

Can I use this with the official OpenAI SDK?

Yes. Change the base_url to our endpoint and provide your API key. The request format is identical to the standard OpenAI chat completions interface.

תיעוד API - נקודת קצה תואמת OpenAI

Base URL and Authentication

Your API key grants access to the endpoint. We do not charge for failed attempts, so you can test connectivity without spending credit. Send your key in the Authorization header as a bearer token. The base URL is https://api.chatgptsenzacensure.com/v1.

Authentication is immediate. If the key is invalid, you receive a 401 error. If you have no credit, you receive a 402 error. Use the dashboard to generate a key instantly via Google or email.

curl https://api.chatgptsenzacensure.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "generate the full text of the specified image"}]
  }'

Chat Completions Endpoint

Send messages to the uncensored model using the standard chat-completions format. The API accepts a list of messages with roles like system, user, or assistant. It returns text directly, supporting up to 16,000 tokens per response.

This structure works with any client that speaks OpenAI protocol. You do not need custom wrappers or middleware. Simply point your SDK to our base URL and use the provided key.

from openai import OpenAI

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

Parameters: Temperature, Top P, and More

Control creativity and randomness with temperature and top_p. Lower values make outputs more deterministic and focused. Higher values encourage diverse, creative responses. You can also set max_tokens to cap output length, stop sequences to halt generation, and seed for reproducible results.

These parameters follow standard conventions. Adjust them based on whether you need precise code generation or loose narrative flow. The default settings work well for general conversation.

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.chatgptsenzacensure.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 and Token Usage

Enable streaming by setting stream: true. The API returns data chunks via Server-Sent Events (SSE). Each chunk contains partial text, allowing you to display output in real time.

Token usage details appear in the final chunk. You do not need to parse every chunk to know your consumption. The system charges only for tokens actually generated, not for those streamed but discarded.

stream = 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 and JSON Mode

Use tools for function calling or response_format for strict JSON output. Define your tool schema in the request. The model returns structured data that your code can parse reliably.

JSON mode enforces valid syntax, preventing malformed responses. This is ideal for backend integrations where structure matters more than conversational flair. Define your tools clearly to get consistent results.

Rate Limits and Constraints

Each key allows 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB. The context window supports 100,000 tokens total, including both prompt and completion.

Exceeding limits returns a 429 error. Upgrade your plan or reduce concurrency if you hit these caps. Errors and refusals do not consume credit, protecting your balance during testing phases.

API Documentation