Skip to main content
OpenCode speaks Chat Completions. Private AI Proxy configures it automatically.

With Private AI Proxy

  1. Install Private AI Proxy, choose a Phala profile, sign in, and turn on Protected.
  2. On the Agents screen, connect OpenCode.
  3. Restart OpenCode.
The app writes the provider into ~/.config/opencode/opencode.json with an agent-scoped token for its local API, and restores the file when you disconnect or stop Protected. From the CLI, the same connection is:

Without the Proxy

Create a key under Private AI → API Keys in the Phala dashboard. Export your Phala API key, then add a custom provider to opencode.json in your project:
opencode.json
Start OpenCode, run /models, and select the Phala model. The key is read from the process environment. For another model, use its ID and limits from the model catalog. 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

Run /models and confirm a phala/ model is selected, then run one bounded tool task.

Troubleshooting