# iPhone and iPad for your AI agents.

Your agent opens your iOS app, reads the screen and taps through it with the same API and MCP calls it uses on Android. Mobilebox iPhone sandboxes cost $0.05 a minute, billed by the second; its cloud Android phones cost $0.01 and were ready in 19.4 s in our November 2026 benchmark.

[Start with iPhone](https://mobilebox.dev/signup?device=iphone) [See pricing](https://mobilebox.dev/pricing)

Sign up with GitHub. New workspaces get free credit.

## How it works.

Your agent keeps its calls. The phone underneath changes.

[Devices in the API](https://mobilebox.dev/docs/reference#devices)

1. Start with iPhone
   Sign up and pick iPhone or iPad.

2. Create an iPhone
   Your agent asks for `platform: "ios"`, over REST or MCP.

3. Run your agent
   It reads the screen as numbered elements and taps, types and swipes by number, as on Android.

## What you get

One API and one MCP server for every phone.

### iPhone and iPad

- The same observe and act calls

- $0.05 per phone-minute

- Billed per second while it runs

### Android too

- Cloud Android 14 phones (arm64)

- $0.01 per phone-minute

- One key for both

### Getting started

- Sign up with GitHub

- Free credit for new workspaces

- Add credits from your dashboard

## Questions

Getting started, pricing and the API.

How do I get iPhone sandboxes?

Sign up, create an API key, and ask for `platform: "ios"` when you create a phone. Your agent gets the same screen and actions as on Android.

Will it work with Claude Code, Codex and Cursor?

It uses the same hosted MCP server and REST API, so a client that drives Android phones makes the same calls.

What does it cost?

$0.05 per phone-minute for iPhone and iPad, billed by the second while the phone runs. Android cloud phones are $0.01 per phone-minute; dedicated devices start at $79 a month. See [pricing](https://mobilebox.dev/pricing).

## Read more

[iOS testing for AI coding agents: what runs where today Every iOS path for an agent runs on a Mac: Simulator, XCUITest, mobile-mcp, macOS CI runners and device farms, and where Mobilebox iPhone sandboxes fit. Guides3 min read](https://mobilebox.dev/blog/ios-testing-for-ai-coding-agents) [Your agent built an iPhone app. How do you test it? Simulator first, an outcome-based XCUITest second, a real iPhone third, then a device lab: a Mac-based checklist for iPhone apps an AI agent wrote. Guides3 min read](https://mobilebox.dev/blog/test-iphone-apps-your-agent-built)

## Try it in your agent in 60 seconds

Paste this into Claude Code, Cursor, Codex or any agent that can read a web page. It asks for your email, gets its own key at once and adds the phone tools; the 6-digit code from your inbox keeps the workspace.

```
Set up Mobilebox for me: read https://mobilebox.dev/setup.md?via=ios and follow it.
```

[What your agent reads](https://mobilebox.dev/setup.md?via=ios)

## Next questions

- [Mobilebox or BrowserStack?](https://mobilebox.dev/blog/mobilebox-vs-browserstack?via=next-browserstack)

- [Cloud phone or a local emulator?](https://mobilebox.dev/blog/mobilebox-vs-local-emulator?via=next-emulator)

- [Mobilebox, Limrun or Mobilerun?](https://mobilebox.dev/blog/mobilebox-vs-limrun?via=next-limrun)

- [How do I add it to Cursor, Codex or VS Code?](https://mobilebox.dev/blog/android-mcp-cursor-codex-vscode?via=next-setup)

- [Can my agent run 50 phones in parallel?](https://mobilebox.dev/blog/run-android-phones-in-parallel?via=next-parallel)

- [Can each phone get a residential IP?](https://mobilebox.dev/blog/residential-ip-per-phone?via=next-residential-ip)

- [Does my agent stay logged in between runs?](https://mobilebox.dev/blog/park-resume-android?via=next-logins)

- [Can I watch my agent work live?](https://mobilebox.dev/live-view?via=next-live)