# Add AI to your app

> Give your Cloud app AI features for its users. No AI account or key to buy - requests go through Playcode AI Gateway and use your credits.
> Source: https://playcode.io/docs/add-to-your-app/ai-in-your-app - last reviewed 2026-10-10.
> Ask Playcode's agent: "Add a button to my product form that writes the description with AI." It switches on AI for the app if needed, writes the backend code and tests it with one real request, which uses your credits.

Your Cloud app can use AI for the people who use it: a button that drafts a product description, a chat that answers your customers. The app calls the models through Playcode AI Gateway, so there is no AI account or key to buy, and each request uses your workspace's credits.

## Do it yourself

1. Check that the app has AI. In the project, open **Settings**, choose **Secrets** and look for `PLAYCODE_AI_URL`, marked **Managed**. If it is missing, ask the agent to switch on AI for the app: it adds the setting and restarts the app.
2. Call the model from the app's backend. A new Cloud app has an AI service in `backend-nest/src/ai/`: `complete()` answers with text, and `stream()` answers while the model writes.

   ```ts
   import { Injectable } from '@nestjs/common'
   import { AiService } from '../ai'

   @Injectable()
   export class DescriptionService {
     constructor(private readonly ai: AiService) {}

     write(product: string): Promise<string> {
       return this.ai.complete({
         system: 'Write a two-sentence product description. Plain text only.',
         prompt: product,
       })
     }
   }
   ```

3. Give the feature an endpoint of its own in the backend, with a sign-in check, and call that endpoint from the page. The browser never calls Playcode AI Gateway and never sees the key.
4. Try the feature once. In **Settings**, **Usage**, the project's **AI Gateway** row counts the requests, with their calls and tokens.

> [!WARNING]
> Put a sign-in check on every AI endpoint. An endpoint that anyone on the internet can call spends your credits.

> [!COST]
> Each request uses credits at the model's own rate, the same rate the agent pays for that model in the chat. Unlike your own building, this spending follows your users. Watch **Settings**, **Usage** after you launch an AI feature, and consider [auto-recharge](/docs/account-and-billing/top-ups-and-auto-recharge).

### Models

Your app names a model by its id. The AI service uses `claude-haiku-4-5-20251001` unless you pass another, like `claude-sonnet-5` for harder tasks. Ask the agent which models your app can use: it reads the current list and prices from Playcode.

The gateway speaks each model maker's own interface, so their official SDKs work with two changes: `PLAYCODE_SECRET_KEY` as the SDK's `apiKey`, and Playcode's address as its base URL. Claude models use the Anthropic SDK at `PLAYCODE_AI_URL` plus `/anthropic`; other models use the OpenAI SDK at `PLAYCODE_AI_URL` plus `/openai`.

```ts
import Anthropic from '@anthropic-ai/sdk'

const client = new Anthropic({
  apiKey: process.env.PLAYCODE_SECRET_KEY,
  baseURL: process.env.PLAYCODE_AI_URL + '/anthropic',
})
```

## If it doesn't work

### The request fails with 402 and `insufficient_balance`

The workspace is out of credits. Add credits; do not retry the request in a loop.

### The answer stops early with `playcode_balance_exhausted`

The credits ran out while the model was answering. The text that arrived was delivered and billed.

### The request fails with 429 and `rate_limited` or `daily_cap`

A request limit was reached. The error body's `playcode` part says which limit refused and what remains. Wait, then try once more.

### "model '...' is not available"

Playcode does not offer that model id through this SDK, or the id is misspelled. Ask the agent for the list.

### The request fails with 403 and `missing_scope`

The app's key cannot use AI yet. Ask the agent to switch on AI for the app: it renews the key and restarts the app.

### The request fails with 401 and `invalid_key`

The app uses an old key. A `PLAYCODE_SECRET_KEY` line in the project's `.env.local` file can hide the current one: remove that line. See [Secrets and environment](/docs/publish/secrets-and-environment).

### The response has the header `x-playcode-error-source: upstream`

The model's own provider refused the request, for example for a wrong parameter or an input that is too long. Fix the request.

## Limits

- AI needs a Cloud app. A static site has no server to keep the key.
- The key works only through Playcode AI Gateway. It is not a key for a model maker's own API.
- Model ids pass through unchanged, with no aliases. A model that is not in Playcode's list is refused.
- The models on offer and their prices change over time. Ask the agent before you choose.
- Requests pause when the workspace's credits run out. See [Credits and balance](/docs/account-and-billing/credits-and-balance).