Overview
How API keys, inference, and c8s attestation work in the Confidential Inference API.
The Confidential Inference API uses one public gateway in a confidential c8s cluster.
Client → gateway → inference router → inference workersThe gateway authenticates the API key. The inference router and workers do not receive that key.
Use the service
- Obtain an API key from Confidential AI.
- Call
/v1/modelsto get the available model ID. - Call
/v1/chat/completionsor/v1/completionswith the key.
Verify the deployment
Call /attestation with a fresh 32-byte nonce before you send sensitive
input. This endpoint does not require an API key.
The response contains c8s evidence for the gateway, router, and inference workers. An independent verifier checks the confidential VM base image, Intel TDX evidence, nonce, c8s operator key, allowlist, workload identity, OCI image digest, and effective command.
Attestation proves what c8s approved and launched. It does not prove that the service is healthy or that model output is correct.
What to read next
- API Spec gives all current endpoints, request examples, authentication rules, and errors.
- c8s architecture explains the confidential cluster trust boundary.
- c8s verification model explains how to verify c8s evidence.