Phala Cloud Documentation — Private AI on TEE

Codex speaks the Responses protocol. Private AI Proxy configures it automatically.

With Private AI Proxy

Install Private AI Proxy, choose a Phala profile, sign in, and turn on Protected.
On the Agents screen, connect Codex and pick a model from the verified catalog.
Start codex.

The app adds a custom model provider to ~/.codex/config.toml that points at its local API with an agent-scoped token, and restores the file when you disconnect or stop Protected. From the CLI, the same connection is:

pap agents connect codex

Without the Proxy

Create a key under Private AI → API Keys in the Phala dashboard. Add Phala as a custom provider in the user-level configuration; Codex ignores model_provider and model_providers in a project-local .codex/config.toml.

export PHALA_AI_API_KEY="YOUR_PHALA_API_KEY"

~/.codex/config.toml

model = "z-ai/glm-5.3"
model_provider = "phala"

[model_providers.phala]
name = "Phala"
base_url = "https://inference.phala.com/v1"
env_key = "PHALA_AI_API_KEY"
wire_api = "responses"

Pick the model from GET /v1/models; choose one that declares tools. 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

Start codex and run one bounded tool task. With the Proxy, the provider in config.toml points at http://127.0.0.1:4180/v1; without it, at https://inference.phala.com/v1.

Troubleshooting

Symptom	Check
Codex ignores the Proxy	Confirm Connected in the app and that Protected is on, then restart `codex`.
Codex still uses the default provider	Confirm `model_provider = "phala"` is at the top level of the user-level file.
Chat works but tools fail	Choose a model that declares `tools` in the live catalog.

​With Private AI Proxy

​Without the Proxy

​Check the Connection

​Troubleshooting

​Related

With Private AI Proxy

Without the Proxy

Check the Connection

Troubleshooting

Related