Send your first API request

Create an API key, install the SDK, and send a chat completion request.

• Install the Python or TypeScript SDK
• Send a request to a Mistral model
• Print the model's response

Everything here is the foundation for the agent and RAG quickstarts that follow.

Time to complete: ~5 minutes

• Python 3.9+ or Node.js 18+ installed on your machine.
• A Mistral AI account. Create account ↗
• A Mistral API key. The Experiment plan is free — no credit card required. Follow the Activate Studio and generate an API key quickstart if you don't have one yet.

1. Open Studio›API keys ↗.
2. Click Create new key.
3. Give the key a name (for example, quickstart) and click Create.
4. Copy the key to your clipboard. The key appears only once; if you lose it, generate a new one.
5. Set the key as an environment variable in your terminal:

export MISTRAL_API_KEY="your_api_key_here"

export MISTRAL_API_KEY="your_api_key_here"

pip install mistralai

pip install mistralai

Create a file and add the following code:

# quickstart.py
import os
from mistralai import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"])

response = client.chat.complete(
    model="mistral-large-latest",
    messages=[
        {"role": "user", "content": "What is Mistral AI?"}
    ],
)

print(response.choices[0].message.content)

# quickstart.py
import os
from mistralai import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"])

response = client.chat.complete(
    model="mistral-large-latest",
    messages=[
        {"role": "user", "content": "What is Mistral AI?"}
    ],
)

print(response.choices[0].message.content)

python quickstart.py

python quickstart.py

The terminal prints a short description of Mistral AI. If it doesn't, check the error table below.