Integrate the Uncensored Model in 5 Minutes

Base URL and Authentication

Start by pointing your client at https://api.keyapimistralai.com/v1. Pass your key in the standard Authorization header as a bearer token. This works with the official OpenAI SDKs and any compatible client by changing base_url and the API key. No extra configuration is required for authentication.

Send Your First Chat Completion

Make a POST request to /v1/chat/completions with the model ID "uncensored". The endpoint accepts text in and returns text out. You can set parameters like temperature and top_p to control creativity. Errors and refusals are free, so you only pay for real token usage. Here is a basic curl example:

Copycurl https://api.keyapimistralai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top three installation steps for Linux"}]
  }'

The response includes token counts for billing transparency.

Python SDK Integration

Install the official OpenAI package and configure the client to use our base URL. Set the model to uncensored for content-unrestricted responses. This approach lets you reuse existing code from other providers. The SDK handles JSON serialization and retry logic automatically. Configure your key via environment variables or directly in the client initialization.

Copyfrom openai import OpenAI

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

This setup ensures your Python applications integrate seamlessly with our API.

Node.js SDK Setup

Use the openai npm package to connect to our service. Initialize the client with the correct base URL and your API key. Send messages using the chat completions endpoint. Node.js developers can leverage existing libraries built for OpenAI compatibility. The response structure matches standard OpenAI formats for easy parsing.

Copyimport OpenAI from "openai";

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

Remember to handle async operations correctly when processing the response.

Enable Streaming with Server-Sent Events

Set stream: true in your request to receive token-by-token updates. The final chunk includes the total token usage for billing. Streaming reduces perceived latency for end-users. Server-sent events provide a reliable way to handle partial responses. Configure your client to process each chunk as it arrives.

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)

This method is ideal for chat interfaces where real-time feedback is critical.

Limits, Errors, and Context Window

Our API supports a 100,000 token context window for complex tasks. Max output is 16,000 tokens per request. You are limited to 300 requests per minute and 8 concurrent requests per key. A 401 error means your key is invalid. A 402 error indicates insufficient prepaid credit. A 429 error signals you have hit the rate limit. Errors are free, so you do not pay for failed requests. Manage your keys carefully since one active key replaces the old one.