Quickstart for Mistral users

Base URL & Authentication

To use the API, point your client to https://api.mistralapi.top/v1. Authentication relies on a bearer token included in the Authorization header. You generate this key via the Get API key page using either a Google account or a standard email/password setup. The key is displayed immediately upon creation. Keep this token secure, as it grants full access to your prepaid credit. Unlike standard providers, we do not require a phone number or credit card for the initial trial credit activation.

Our service is designed to drop directly into existing Mistral or OpenAI client configurations. Simply update the base_url property in your SDK instance. The endpoint structure matches the standard /v1/chat/completions format, ensuring that your existing code works without modification. We support a single model ID, uncensored, which handles all text generation tasks.

Chat Completions Endpoint

The core interaction happens via the POST /v1/chat/completions endpoint. You send a JSON body containing your model ID, messages array, and optional parameters. The API returns a text response or structured data if you specify JSON mode. This endpoint is the primary way to interact with the LLM. It supports both standard synchronous requests and streaming responses. Every request consumes tokens from your prepaid balance based on input and output volume.

Errors are handled via standard HTTP status codes. If your key is invalid, you receive a 401. If you run out of credit, you receive a 402. Rate limits are enforced at 300 requests per minute and 8 concurrent connections per key. Use the following example to verify your connection and key validity.

Copycurl https://api.mistralapi.top/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."}]
  }'

Streaming Responses (SSE)

For lower latency and better user experience, enable streaming by setting stream: true in your request body. The API returns a Server-Sent Events (SSE) stream. Each chunk contains a partial response. The final chunk includes the complete token usage statistics for the request. This allows your application to display tokens as they are generated, rather than waiting for the full completion. Streaming is ideal for chat interfaces where immediate feedback is critical.

When using streaming, ensure your client correctly parses the SSE format. The choices array in each chunk will contain delta content. You must accumulate these deltas to construct the full response. Token usage is only available in the last event of the stream. Use this method to keep your users engaged while the model processes complex prompts.

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)

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.mistralapi.top/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.top/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);