> For the complete documentation index, see [llms.txt](https://docs.appmixer.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.appmixer.com/connector-configuration/mistral.md).

# Mistral AI

https\://console.mistral.ai

The Mistral AI connector (*AI* > *Mistral AI*: *Send Prompt*, *Describe Images*, *Generate Embeddings*, *Extract Document Text*, *Create Transcription*, *Create Speech*, *Moderate*, *List Models*, *List Voices*, *Make API Call*) authenticates with a Mistral API key. Each user enters their own key when they connect an account in the Designer, so you do not need to register an app with Mistral.

## Get an API key

1. Sign in to Mistral AI Studio at [console.mistral.ai](https://console.mistral.ai). Create an account if you do not have one.
2. In the left sidebar, open *API Keys*.
3. Click *Create new key*.
4. Enter a *Name* for the key and set an *Expiration* date. Choose any *Connector access* scope. The scope only controls access to Mistral's own Connectors, and the Appmixer connector does not use them.
5. Click *Create new key* and copy the key. Mistral shows the full key only once.
6. In the Appmixer Designer, connect a Mistral AI account and paste the key into the *API Key* field. Appmixer checks the key by listing the available models.

New accounts start in Free mode. Free mode gives API access without a credit card, but usage and rate limits apply. For production use, choose a paid plan in Studio. Requests over the workspace limits fail with rate-limit errors.

## Backoffice configuration

You do not need any Backoffice configuration. The connector reads one optional key that changes how it caches lists.

Configuration ID: `appmixer:ai:mistral`. See [Connector Configuration](https://docs.appmixer.com/getting-started/services) for how to set it.

* `listCacheTTL` – optional. How long, in milliseconds, the connector caches the model list and the voice list (used by *List Models*, *List Voices* and the model and voice selectors in the components). Each API key has its own cache. Default: `120000` (2 minutes).

```bash
appmixer service-config set appmixer:ai:mistral -u -d '{
  "listCacheTTL": 120000
}'
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.appmixer.com/connector-configuration/mistral.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
