Phala Cloud Documentation — Private AI on TEE

Cline uses Chat Completions through its OpenAI Compatible provider. Private AI Proxy does not configure it automatically; enter the app’s Local API values by hand.

With Private AI Proxy

Install Private AI Proxy, choose a Phala profile, sign in, and turn on Protected.
Open Cline’s settings (gear icon), select OpenAI Compatible under API Provider, and enter the Local API values:
Field Value
Base URL http://127.0.0.1:4180/v1
API Key The client key from the app’s Overview screen
Model ID z-ai/glm-5.3, or another chat model from the app’s verified catalog
Start a task.

Requests succeed only while Protected is on. From the CLI, pap token show prints the client key and pap models list lists the catalog. Keep the client key private.

Without the Proxy

Create a key under Private AI → API Keys in the Phala dashboard. Open Cline’s settings (gear icon) and select OpenAI Compatible under API Provider, then enter the following provider settings:

Base URL: https://inference.phala.com/v1
API Key: Your Phala API key
Model ID: z-ai/glm-5.3

Choose another chat model from /v1/models and copy its context and output limits when entering a model by hand. This path does not verify attestation locally; use Private AI Proxy or the TypeScript ACI Verifier. Every model on this endpoint runs in a TEE.

Check the Connection

Use Cline’s Verify action, then run a read-only request in a disposable repository and confirm the selected provider and model.

Troubleshooting

Symptom	Check
Verify fails with the Proxy	Protected must be on; copy the client key again.
Verify fails without the Proxy	Keep `/v1` in the base URL and check the API key.
Tool calls fail	Choose a model that declares `tools` in the live catalog and repeat Verify.