Quickstart: uncensored ai for coding API

Prerequisites and base URL

Get your API key from the dashboard. Use this base URL for all requests: https://api.uncensoredaiforcoding.com/v1. It works with any OpenAI SDK.

Install the official SDK

Install the package in your environment. This ensures compatibility with the uncensored coding AI standard.

Copyfrom openai import OpenAI

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

Make your first request

Send a simple completion to test the connection. The model id is uncensored.

Copycurl https://api.uncensoredaiforcoding.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "get current unix timestamp in python"}]
  }'

Enable streaming for real-time output

Stream responses to handle long code blocks efficiently. Use the stream flag.

Copyimport OpenAI from "openai";

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

Handle errors and usage limits

Expect 429 errors if you hit 300 requests per minute. Context window is 100,000 tokens. Max output is 16,000 tokens.

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)

Use JSON mode for structured data

Force structured output for your code parsers. Set response_format to {"type": "json_object"}.