API Documentation for developers

Base URL and Authentication

Point your SDK or HTTP client to https://api.sowhichdoiuse.com/v1 and include your API key in the Authorization header.

Generate a key on the Get API key page using Google or email; it displays instantly with no phone number required.

Each account holds one active key that replaces the previous one upon regeneration.

We do not offer card or bank payments, so ensure your prepaid credit covers your initial usage.

First Request with cURL

Send a standard chat-completions request using the uncensored model ID.

This simple command verifies connectivity and confirms your account has sufficient prepaid tokens.

Errors like 401 indicate an invalid key, while 402 signals exhausted credit.

Streaming is supported, but this example uses a standard blocking response for simplicity.

Copycurl https://api.sowhichdoiuse.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "return a list of open source libraries for real time chat"}]
  }'

Python SDK Implementation

Use the official OpenAI Python library to interact with our uncensored LLM.

Set the base URL to our endpoint and provide your API key from the dashboard.

Specify the model as uncensored to ensure you receive the tuned, unrestricted responses.

This approach works for both simple text generation and more complex parameter tuning.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.sowhichdoiuse.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.js Integration

Integrate the API into your JavaScript applications using the OpenAI Node SDK.

Configure the client with our base URL and your unique API key.

The SDK handles the request formatting automatically, allowing you to focus on application logic.

Ensure you handle asynchronous responses correctly to maintain application performance.

Copyimport OpenAI from "openai";

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

Enable streaming by setting the stream parameter to true in your request.

Server-Sent Events (SSE) deliver tokens as they are generated, reducing perceived latency for end-users.

The final chunk contains the complete token usage statistics for accurate billing and monitoring.

This method is ideal for chat interfaces that require real-time text rendering.

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

Our context window supports 100,000 tokens for both prompt and completion combined.

Rate limits cap requests at 300 per minute per key, with a concurrency limit of 8 simultaneous requests.

Request bodies must not exceed 8 MB, and errors are free of charge.

Use 401 for authentication failures, 402 for insufficient credit, and 429 for rate limiting to manage your application flow effectively.