OpenAI-compatible API reference

Authentication and base URL setup

Start by retrieving your API key from the dashboard. Use the MISTRALNSFW_API_KEY header for every request to our base URL at https://api.mistralnsfw.com/v1. This works with any OpenAI-compatible client because we follow the standard schema.

The /v1/chat/completions endpoint

Send a POST request to /v1/chat/completions with your model ID set to "uncensored". The endpoint accepts standard parameters like temperature and stop. You pay only for tokens used, with input at $0.15 per 1M tokens and output at $0.50 per 1M tokens.

Copycurl https://api.mistralnsfw.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top ten python libraries for data science"}]
  }'

Python SDK integration

Install the official openai package and point it to our base URL. Set the model to "uncensored" to access the uncensored generation capabilities. This approach lets you reuse existing code with minimal changes to your project structure.

Copyfrom openai import OpenAI

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

Node SDK integration

Use the Node.js SDK to initialize the client with the correct base URL and API key. Define your messages array and call the chat.completions.create method. This setup ensures compatibility with standard tools while delivering the specific uncensored model behavior you need.

Copyimport OpenAI from "openai";

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

Streaming responses and token usage

Enable streaming by setting stream: true in your request. The server returns chunks via Server-Sent Events (SSE). The final chunk contains the total token usage for the request, allowing you to track costs accurately in real-time.

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)

Rate limits and request constraints

Each key is limited to 300 requests per minute and 8 concurrent requests. The maximum context window is 100,000 tokens, with a max output of 16,000 tokens per request. Errors like 401 (invalid key), 402 (no credit), and 429 (rate limit) are standard HTTP responses.