Uncensored API quickstart

Install the official OpenAI SDK

Start by installing the library that powers your existing infrastructure. We support the standard client used across the industry, ensuring your code remains portable. This avoids vendor lock-in while giving you access to our uncensored model via the same interface.

Copyfrom openai import OpenAI

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

Set your base URL and API key

Point your client to our dedicated endpoint to bypass standard filters. Configure your environment variables immediately to keep credentials secure. Our API expects a specific base URL and a valid key for authentication.

Copyimport OpenAI from "openai";

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

Send your first request to /v1/chat/completions

Call the chat endpoint with your system and user messages. The model processes the input and returns a direct text response without unnecessary refusals. Use the uncensored model ID for unrestricted outputs.

Copycurl https://api.kimicontextwindow.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summarize the RFC 9001 document in 200 words"}]
  }'

Handle streaming responses via SSE

Enable streaming to receive tokens as they generate, reducing perceived latency. The server sends Server-Sent Events, allowing your application to display output progressively. This is ideal for chat interfaces where users expect immediate feedback.

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)

Enable JSON mode or function calling

Structure your output for programmatic use by enabling JSON mode. You can also define tools for function calling to integrate with external systems. Both features work with our single uncensored model for reliable data extraction.

Check usage, limits, and errors

Monitor your token count and request limits to avoid service interruptions. Our API enforces a 100,000 token context window and a 300 requests per minute limit. If you see a 401, check your key; a 402 means you need to top up via crypto; and a 429 indicates you hit the rate limit.