---
title: "Get hardware attestation evidence"
method: GET
path: "/attestation/attest"
tags: ["Attestation", "dev-api"]
---

# Get hardware attestation evidence

`GET /attestation/attest`

## Request

- Base URL: `https://gateway.prem.io`
- URL: `https://gateway.prem.io/attestation/attest`
- Auth: one of:
  - HTTP bearer
  - API key in header `Authorization`
  - none

Fetch the standard v2 attestation report for the confidential environment that serves a model. Use Reticle to verify the report before sending protected inference requests.

## Query parameters

- `nonce` string, required
- `model` string, required

## Response `200`

Standard confidential-VM attestation report containing the workload manifest, CPU evidence and optional GPU evidence.

- GetCvmAttestationResponse: Unified CVM attestation report.
  - `manifest` object, required: Metadata of the CVM that produced the report
    - `podvm_version` string, required: PodVM image version the CVM booted from
    - `workload_id` string, required: Workload identifier taken from the CVM init-data
  - `cpu` object, required: CPU attestation evidence. Vendor quote internals are defined by the attestation server.
  - `gpu` union, required: GPU attestation evidence, if any.
    - 'Absent'
    - object
      - `Nvidia` string, required: NVIDIA detached EAT token (JWT) bound to the CPU report

## Other responses

- `400`: Bad request
- `429`: Too many requests
- `502`: Attestation report temporarily unavailable

## Changes

- **2026-11-13** `d46bc3931b34`: 1 info
  - endpoint added

[Operation history](https://skmtc.dev/premai-io/apis/prem-studio-api/changes/attestation/attest/get.md)

---

[API](https://skmtc.dev/premai-io/apis/prem-studio-api.md) - [All operations](https://skmtc.dev/premai-io/apis/prem-studio-api/llms.txt) - [OpenAPI document](https://skmtc.dev/premai-io/apis/prem-studio-api/revisions/d46bc3931b34?raw)