Mistral AI

Mistral AI serves its own models and open models from other labs through its API. Mistral AI supports Chat Completions requests.

Even though Mistral AI is a built-in provider, it still requires you to bring your own key because you can’t pay for it with credits at this time.

Setup

Create an access key

Follow the quickstart to create an access key in app.ngrok.ai.

Store your Mistral AI API key

Create an API key in your Mistral AI account. Then add a provider key.

Create a configuration

Create an access key configuration with a mistral routing rule and allow Mistral AI in the access scope.

Assign and send requests

Assign the configuration to your access key and send requests with your access key:

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.ngrok.ai/v1",
    api_key="ng-xxxxx-g1-xxxxx",
)

response = client.chat.completions.create(
    model="mistral:z-ai/glm-5.3",
    messages=[{"role": "user", "content": "Hello!"}]
)

Other providers also serve GLM-5.3, so the mistral: prefix keeps the request on Mistral AI.

Available models

See the model catalog. To call a Mistral AI model that isn’t in the catalog yet, send its ID with the mistral: prefix. See catalog updates.

Concepts

Getting Started With

SDKs

Agents

Guides

Observability

Examples

Reference

API Reference

Setup

Available models

Next steps

​Setup

​Available models

​Next steps

Setup

Available models

Next steps