API Reference & Quickstart

Authentication & Rate Limits

Start by generating your key on the dashboard. The uncensored AI API uses standard bearer tokens for authentication. You get 300 requests per minute and 8 concurrent connections. Errors and refusals consume no credits.

Include your key in the header. The base URL is HTTPS://api.uncensoredaipricing.com/v1. Sign up with Google or email. No phone number required.

Chat Completions Endpoint

Send text to the uncensored LLM API via POST /v1/chat/completions. The model id is "uncensored". It handles prompt + completion together within a 100,000 token context window. Max output is 16,000 tokens.

Set the API key. Here is a curl example:

Copycurl https://api.uncensoredaipricing.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Calculate the monthly cost for 50 million tokens."}]
  }'

Streaming Responses (SSE)

Receive real-time tokens via Server-Sent Events. Streaming reduces perceived latency for long responses. Use the stream parameter in your request. The last chunk includes final token usage.

Here is a Python example:

Copyfrom openai import OpenAI

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

JSON Mode & Function Calling

Enforce structured output with response_format json_object. Enable function calling with tools and tool_choice. Parameters like temperature and top_p control randomness. Use stop sequences for clean cuts.

Here is a Node example:

Copyimport OpenAI from "openai";

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

Token Limits & Context Window

The context window holds 100,000 tokens total. Requests over 8MB or 300 RPM get rejected. Set max_tokens to 16,000. Default is 2,048. Prepaid credit never expires. Errors are free.

Here is a streaming example:

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)

Error Codes & Refusals

401 means an invalid key. 402 indicates no credit. 429 signals rate limits. Minors in sexual content trigger a hard refusal. Other adult content passes. Check the status code. Fix your key or top up.