> ## 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.

# TextCortex plugin

> Text generation with TextCortex - list the models, read the credit balance and enabled capabilities, run chat completions and single responses, generate images, and search the web.

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

Create a key in your TextCortex account's API settings. The plugin sends it as `Authorization: Bearer <key>`. Keep it server-side.

Things to know before you call:

* **Every generation is paid.** `chat.completions`, `responses.create` and `images.create` spend credits and produce something new, so they are `destructive` and need approval. `web.search` also spends credits per search, but it only returns data, so it is a `read`. Check `balance.get` for what is left.
* **A 402 means the credits ran out.** Waiting does not help, so the plugin never retries a 402. Errors are core's `ApiError` with the request body removed; `textCortexErrorDetails(error)` reads the provider's message, code and per-field details.
* **The models route is the place to start.** `models.list` returns the IDs `chat.completions` and `responses.create` accept. Use the base ID rather than a deprecated `-thinking` variant; on `chat.completions`, set `reasoning_effort` instead (`responses.create` does not take it).
* **Two request shapes.** `chat.completions` takes an OpenAI-style `messages` array. `responses.create` takes a single `input` string with optional `instructions`, and stores nothing: the plugin pins `store: false` and rejects `store: true`.
* **Text is the supported content.** `chat.completions` sends plain-text messages. Image inputs, tool calls and streaming are not modelled, and the request schemas are strict, so an unsupported field such as `tools` or `stream` is rejected before anything is sent or billed.
* **Errors come in three shapes.** The chat route answers the OpenAI `{ error: { message, type } }` envelope, TextCortex's own routes answer `{ message, status }` or `{ detail }`, and a validation failure puts an array in `detail`. All three are parsed, and a validation array keeps each field's location.
* **No retried paid calls.** The plugin replays a 5xx only on a GET. A repeated completion can produce and bill a second answer, and TextCortex promises no idempotency key.

**What you get:**

* 7 typed API operations

## Setup

**1. Install**

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

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

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

```bash bun theme={null}
bun add corsair @corsair-dev/textcortex 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 { textcortex } from '@corsair-dev/textcortex';

export const corsair = createCorsair({
	plugins: [
		textcortex(),
	],
	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 TextCortex API key before the first call: `pnpm corsair setup --plugin=textcortex --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}
> textcortex()
> ```
>
> 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: 'textcortex',
	tenantId: 'acme',
});
// redirect the user's browser to connectUrl
```

## Example API calls

**List the available models**

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

**Ask a model a question**

```ts theme={null}
const tenant = corsair.withTenant('acme');
await tenant.textcortex.api.chat.completions({
	model: 'gpt-6-luna',
	messages: [{ role: 'user', content: 'Hello' }],
});
```

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

## What's next

> [card] [API reference](https://docs.corsair.dev/plugins/textcortex/api.md)
>
> Every `textcortex.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.