Skip to main content
Phala runs models in confidential computing hardware. Use a Confidential AI API key. Add your key to Enconvo to use those models in chats, Agents, and AI Commands. Phala bills the usage to your own account.

​
Connect

1

Get an API key

Create a key in the Phala Cloud.
2

Add it to Enconvo

Open Settings → AI Model → Phala. Under Authentication, paste the key into API Key, then click Validate.
3

Pick a model

Choose a model in Model Name and send a short message. A reply means the connection works.
To keep a second Phala key, for example one for work, click Add New Provider and create another profile.

​
Models and options

To use a different model in one chat, pick it from that chat’s model picker. Validate sends a minimal chat request, up to one output token. Enconvo sets the endpoint for you. Vision and tool calls depend on the model; one model supporting them doesn’t mean the others do. For model details and limits, see the Phala Confidential AI docs.

​
Troubleshooting

Choose a model

Pick a model by task, and see where defaults are set.

Credentials and profiles

Keep several keys, and see what a shared key affects.

Auto Route

Let Enconvo pick the model for each message.

Provider catalog

Every provider, grouped by the feature it powers.