Quickstart: Connect your OpenAI SDK

Prerequisites: SDK and environment

Install the official client library for your preferred language. You will need a modern Python or Node.js runtime and a valid API key from your dashboard. The environment variables should be set securely before initializing the client instance.

Configuration: base_url and API key

Point your SDK to our specific endpoint instead of the default OpenAI host. Use the base URL provided in your dashboard and assign your generated key to the standard authorization header. This ensures all requests route correctly to our uncensored model infrastructure without needing custom headers.

Sending your first chat completion

Make a simple POST request to the chat completions endpoint to verify connectivity. Our uncensored model responds instantly to standard prompts, allowing you to test content generation without immediate refusals. Use the following example to confirm your key works:

Copycurl https://api.mistralopenaicompatibleapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list top 5 linux commands for disk cleanup"}]
  }'

The response confirms the model processed your input within the allowed context window. You can now integrate this logic into your application workflows.

Python SDK implementation

Use the official Python library to handle request serialization automatically. Set the base URL to our domain and pass your API key as the primary authentication parameter. This approach works identically for local testing and production deployments.

Copyfrom openai import OpenAI

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

Ensure you handle exceptions properly, as network errors or invalid keys will raise standard HTTP exceptions. The library manages token counting efficiently for your prepaid balance.

Node SDK implementation

Initialize the client with the correct base URL and API key in your Node.js environment. The SDK supports both synchronous and asynchronous patterns for different use cases. Configure the model ID to "uncensored" for consistent results.

Copyimport OpenAI from "openai";

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

Node users benefit from the same token pricing structure and rate limits as Python users. Monitor your usage dashboard to track prepaid credit consumption accurately.

Streaming responses and limits

Enable streaming to receive tokens progressively, reducing perceived latency for long outputs. Our API supports Server-Sent Events for real-time text generation, which is ideal for chat interfaces. Watch for rate limits (429) and token constraints during high-volume usage.

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)

Each request respects the 100,000-token context window and the 16,000-token output limit. Errors like 401 indicate invalid credentials, while 402 signals insufficient prepaid credit. Keep requests under 8 MB to avoid payload rejections.