API Documentation & Quickstart

Base URL and Authentication

Start every request to https://api.whatisthemostuncensoredai.com/v1 with your API key. This openai compatible API endpoint expects standard headers for immediate connectivity.

• Header: Authorization: Bearer YOUR_API_KEY
• Endpoint: /v1/chat/completions

Copycurl https://api.whatisthemostuncensoredai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a list of the top 10 uncensored models"}]
  }'

Keep your key secure. Rotate it immediately if exposed. No phone number is required for signup. Google or email access grants instant credentials.

Chat Completions Endpoint

Send messages to the single uncensored LLM API endpoint for text generation. The model id is always uncensored.

Copyfrom openai import OpenAI

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

Input text goes into the messages array. Output appears in content. Errors return standard HTTP codes. No complex routing logic exists. Just send the payload and receive the response.

Streaming Responses (SSE)

Enable real-time token delivery by setting stream: true. This uncensored LLM API supports Server-Sent Events for low-latency applications.

Copyimport OpenAI from "openai";

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

Process chunks as they arrive. Token usage details appear in the final chunk. Buffering is minimal. Handle partial responses gracefully. The stream ends when generation completes or an error occurs.

Function Calling and JSON Mode

Use response_format for structured output. Set json_object to enforce strict JSON compliance. This uncensored AI API supports tool definitions for programmatic interactions.

Define tools in the request body. The model returns valid JSON matching your schema. Parse the result in your code. Error handling remains consistent with standard requests.

Token Limits and Context Window

The context window supports 100,000 tokens total. Max output is 16,000 tokens per request. Default max tokens is 2,048 if unspecified.

Prompt and completion tokens count together. Exceeding the limit returns an error. Monitor usage via the response headers. Efficient prompting saves credits. Prepaid credit never expires.

Error Handling and Usage

Handle 401 for invalid keys. Return 402 when credit is insufficient. Rate limits trigger 429 errors after 300 requests per minute.

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)

Errors include detailed messages. Refusals are free. Check the error object for specifics. Retry logic should account for rate limits. Credit deductions happen only on successful token usage.