Quickstart for Mistral users

Base URL & Authentication

Our API is fully compatible with the OpenAI SDKs. You only need to update the base URL and provide your API key. The base URL for this service is https://api.mistralapi.com/v1. Authentication is handled via the Authorization header using a Bearer token. Unlike some providers, we do not require complex routing or vendor-specific headers; just pass your key as you normally would.

• Base URL: https://api.mistralapi.com/v1
• Header: Authorization: Bearer YOUR_API_KEY

Your API key is generated immediately upon signup. Keep it secure, as it grants access to your prepaid credit. There are no monthly subscription fees, only pay-as-you-go pricing based on token usage.

Chat Completions Endpoint

The core of our API is the POST /v1/chat/completions endpoint. It accepts a list of messages and returns a generated response. This endpoint supports the standard message format used by most LLM clients. You must specify the model ID as "uncensored". This model is an open-weight large language model hosted on our servers, tuned to answer without content refusals for lawful adult use.

• Endpoint: POST /v1/chat/completions
• Model ID: uncensored

The API returns text responses only. It does not support images, audio, video, or embeddings. For most developers, this endpoint replaces the standard OpenAI chat endpoint with zero code changes beyond the base URL and model ID.

Python SDK Integration

Using the official OpenAI Python library is the fastest way to integrate. Set the base URL to our endpoint and provide your API key. The code below demonstrates a simple text completion request.

• Install the library: pip install openai
• Set base_url to https://api.mistralapi.com/v1
• Use model="uncensored"

This approach works because our API mirrors the OpenAI response structure. You can use existing libraries for streaming, function calling, and JSON mode without modification.

Node SDK Integration

For JavaScript/TypeScript developers, the openai npm package works seamlessly. Configure the client with our base URL and your API key. This allows you to use the same codebase for both OpenAI and our uncensored model.

• Install the library: npm install openai
• Configure baseUrl to https://api.mistralapi.com/v1
• Specify model: "uncensored"

This compatibility extends to all standard parameters like temperature, top_p, and stop sequences. You can switch between providers easily by changing the client configuration.

Streaming Responses

We support streaming responses via Server-Sent Events (SSE). This allows you to receive tokens as they are generated, reducing perceived latency for users. The final chunk of the stream includes the token usage statistics for billing.

• Set stream: true in your request
• Read chunks from the response
• Parse the final chunk for usage data

Streaming is ideal for chat interfaces and real-time applications. The response format matches the OpenAI streaming standard, so your existing streaming logic will work without changes.

Limits, Errors & Context Window

Our API has specific limits to ensure stability. Each API key supports 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB. The context window is 100,000 tokens total (prompt + completion). If you do not set max_tokens, the default output is 2,048 tokens; otherwise, the max output is 32,000 tokens.

• 401: Invalid API key
• 402: Insufficient credit
• 429: Rate limit exceeded

Premium credit never expires. Errors and refusals are free. If you encounter issues, use the Support page for refunds or account help.

cURL

Copycurl https://api.mistralapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.mistralapi.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.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.mistralapi.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

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)