> ## Documentation Index
> Fetch the complete documentation index at: https://docs.corsair.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Mistral AI plugin

> Mistral AI's model API. Run chat, fill-in-the-middle and agent completions, create embeddings, moderate and classify text, read documents with OCR, transcribe and synthesize speech, and manage models, files, batch jobs and agents.

Use **Mistral AI** through Corsair: one client, typed API calls.

Each operation returns one JSON result: streaming is off for completions, responses, speech and transcription. Files and audio go in as base64; the fields differ per operation: `files.upload` takes `content_base64` and `filename`; `audio.transcribe` takes `content_base64` with `filename`, or `file_url` or `file_id` instead; `voices.create` takes `sample_audio` and an optional `sample_filename`; `ocr.process` takes its `document` as a URL (`{ type: 'document_url', document_url }` for a PDF, `{ type: 'image_url', image_url }` for an image) or as the `file_id` of an uploaded file (`{ type: 'file', file_id }`); `document_url` and `image_url` also accept a base64 data URL such as `data:application/pdf;base64,...` or `data:image/png;base64,...`. `files.getSignedUrl` gives a download link for a file's content, such as a batch job's results.

A batch job runs on Mistral after `batch.create` returns. Follow it with `batch.get({ job_id })` until `status` is SUCCESS (read `output_file` with `files.getSignedUrl`), or FAILED, TIMEOUT\_EXCEEDED or CANCELLED. QUEUED, RUNNING and CANCELLATION\_REQUESTED mean it is still going.

`agents.*` other than `agents.complete` are Mistral beta endpoints. A 422 from Mistral names each rejected field in the error message, for example `body.messages.0.content: Field required`.

**What you get:**

* 52 typed API operations

## Setup

**1. Install**

```bash npm theme={null}
npm install corsair @corsair-dev/mistralai better-sqlite3
npm install --save-dev @types/better-sqlite3
```

```bash yarn theme={null}
yarn add corsair @corsair-dev/mistralai better-sqlite3
yarn add --dev @types/better-sqlite3
```

```bash pnpm theme={null}
pnpm install corsair @corsair-dev/mistralai better-sqlite3
pnpm install --save-dev @types/better-sqlite3
```

```bash bun theme={null}
bun add corsair @corsair-dev/mistralai better-sqlite3
bun add --dev @types/better-sqlite3
```

**2. Add the plugin**

```ts corsair.ts theme={null}
import Database from 'better-sqlite3';
import { createCorsair } from 'corsair';
import { mistralai } from '@corsair-dev/mistralai';

export const corsair = createCorsair({
	plugins: [
		mistralai(),
	],
	database: new Database('corsair.db'),
	kek: process.env.CORSAIR_KEK!,
	multiTenancy: true,
	hub: {
		projectApiKey: process.env.CORSAIR_API_KEY!,
		signingSecret: process.env.CORSAIR_SIGNING_SECRET!,
	},
});
```

With `multiTenancy: true`, scope calls with `corsair.withTenant(id)`. See [Quick start](https://docs.corsair.dev/quick-start.md) for KEK + Hub keys, and [Multi-tenancy](https://docs.corsair.dev/concepts/multi-tenancy.md) for account isolation.

**3. Choose authentication**

> [tab] API Key (Recommended)
>
> Store the Mistral AI API key before the first call: `pnpm corsair setup --plugin=mistralai --tenant=acme api_key=<your-key>` (leave out `--tenant` without `multiTenancy`), or pass it as `key` in the plugin options. With Hub, each tenant enters their own key on the connect page. See [API key auth](https://docs.corsair.dev/concepts/api-key).
>
> ```ts theme={null}
> mistralai()
> ```
>
> More: [API Key](https://docs.corsair.dev/concepts/api-key)

**4. Connect a tenant**

Mint a connect link and send the tenant to it. Hub hosts the page and delivers the result to your app — see [Connect / OAuth](https://docs.corsair.dev/management/connect).

```ts theme={null}
const { connectUrl } = await corsair.manage.connect.createLink({
	plugin: 'mistralai',
	tenantId: 'acme',
});
// redirect the user's browser to connectUrl
```

## Example API calls

**List the models this key can use**

```ts theme={null}
const tenant = corsair.withTenant('acme');
await tenant.mistralai.api.models.list({});
```

**Ask a model a question**

```ts theme={null}
const tenant = corsair.withTenant('acme');
await tenant.mistralai.api.chat.complete({
	model: 'mistral-small-latest',
	messages: [{ role: 'user', content: 'In one sentence, what is retrieval-augmented generation?' }],
});
```

See the full list on the [API](https://docs.corsair.dev/plugins/mistralai/api.md) page.

## What's next

> [card] [API reference](https://docs.corsair.dev/plugins/mistralai/api.md)
>
> Every `mistralai.api.*` operation with input and output types.

> [card] [Connect / OAuth](https://docs.corsair.dev/management/connect)
>
> createLink, Hub delivery, and tenant connect flows.

> [card] [Use with agents](https://docs.corsair.dev/mcp-adapters/mcp-adapters)
>
> Expose this plugin's operations as MCP tools.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.