API Documentation

Authentication and base URL

The API key authenticates your requests. Generate one via Google or email on the Get API key page. Keep it secure. Use this base URL for all calls: https://api.whatisuncensoredai.com/v1.

Set the Authorization header to Bearer YOUR_API_KEY. The key identifies your prepaid account. Errors and refusals do not consume tokens. Only valid completions charge your balance.

Chat completions endpoint

Send messages to the single uncensored model via POST requests. The endpoint is /v1/chat/completions. Pass the model ID as uncensored. The model does not refuse lawful adult, fictional, or controversial topics.

Structure your JSON payload with a messages array. Each message has a role and content. The API returns the generated text in the response.

Copycurl https://api.whatisuncensoredai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate 100 lines of code for a basic API."}]
  }'

Model listing endpoint

Discover available models with a simple GET request. Call /v1/models to list endpoints. The only model available is uncensored. It is an open-weight model tuned for unrestricted generation. It is not GPT, Claude, or any other vendor model.

Use this endpoint to verify connectivity. The response includes model details and ID. No other models are offered. Focus on one endpoint for simplicity.

Streaming and usage data

Enable streaming by setting stream: true in your request. The API returns chunks via Server-Sent Events (SSE). Each chunk contains partial text. The final chunk includes token usage data. This helps you track prepaid balance accurately.

Parse the SSE stream to display real-time output. Handle errors gracefully. Token counts appear only in the last chunk. This design saves memory for long conversations.

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

Control generation with standard parameters. Use temperature for randomness. Set top_p for nucleus sampling. Enable JSON mode with response_format: {"type": "json_object". This ensures structured output for parsers.

Other options include stop sequences, seed for reproducibility, and penalties for presence and frequency. Function calling works with tools and tool_choice. Adjust these to fit your workflow.

Copyfrom openai import OpenAI

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

Rate limits and error handling

Each key allows 300 requests per minute and 8 concurrent requests. The request body must stay under 8 MB. Exceeding these limits returns a 429 status code. Wait and retry. Use exponential backoff for robustness.

Common errors include 401 for invalid keys and 402 for insufficient credit. Credit is prepaid. Top up with crypto to continue. Errors do not charge your balance. The context window is 100,000 tokens total. Max output is 16,000 tokens.

Copyimport OpenAI from "openai";

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