Morph Cloud vs Vercel Sandbox

Morph Cloud

Pause and snapshot keep memory and running processes, and one call branches an instance into several copies. A public OpenAPI file covers 69 operations. No terms of service, privacy policy or security page was found, the free plan includes no compute credit, and the changelog holds one entry from November 2024.

Vercel Sandbox

Active CPU billing, so waiting on model responses costs only memory. Tied to a Vercel team and project even when called from elsewhere, and access tokens reach the whole team.

Morph Cloud

1. Set ttl_seconds and ttl_action when starting an instance. Nothing in the docs stops an instance with no TTL from billing MCUs
2. Pass auth_mode: api_key when exposing an HTTP service. The default is none, which makes the URL public
3. Enable wake_on_ssh before calling exec on an instance that may be paused. There is no separate exec wake setting
4. Use /api/instance/list and /api/snapshot/list with page and limit (default 50, maximum 1,000). The plain list routes return everything
5. On a 503 from snapshot, branch, pause or reboot, wait for the Retry-After value before repeating the call

Vercel Sandbox

1. Call sandbox.stop() when the task is done. Memory bills until the session ends
2. Use Sandbox.getOrCreate with a name so retries land in the same sandbox
3. Set networkPolicy to deny-all for untrusted code. The default is allow-all
4. Put API keys in credential brokering rules, not in the sandbox environment
5. Pass persistent: false for one-off runs so no snapshot is stored or billed