> For the complete documentation index, see [llms.txt](https://docs.cortecs.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cortecs.ai/security-and-compliance/professional-secrecy-agreement.md).

# Professional Secrecy Agreement

Restricted routing for information protected by German § 203 StGB

If you are subject to professional secrecy under **§ 203 StGB**, information entrusted to you in your professional capacity may require additional confidentiality safeguards.

Cortecs supports these workloads through a Professional Secrecy Addendum and routing restricted to a defined set of providers. Both measures are required for the setup described on this page.

{% hint style="warning" %}
**Default routing is not suitable for § 203 workloads.** By default, Cortecs may route requests across its broader provider pool. Do not submit information protected by § 203 StGB until the Professional Secrecy Addendum is in effect and restricted routing has been configured.
{% endhint %}

## Set up restricted § 203 routing

{% stepper %}
{% step %}

### 1. Conclude the Professional Secrecy Addendum

Sign the **Professional Secrecy Addendum** with Cortecs GmbH. Contact [privacy@cortecs.ai](mailto:support@cortecs.ai) to request it.

The addendum establishes the additional confidentiality obligations for the approved provider chain. It does not replace your Data Processing Agreement or other applicable data-protection terms, and it does not replace your own assessment of professional-law requirements or whether a particular disclosure is permitted and necessary.
{% endstep %}

{% step %}

### 2. Restrict routing to approved providers

Use only providers approved by Cortecs for restricted § 203 routing. You can apply the restriction at project level OR per API request:

* In the dashboard, go to **Settings** → **Inference** and select only providers from the approved list below.
* In an API request, pass the exact identifiers from the approved list in `allowed_providers`.

The addendum alone does not restrict routing and does not make default routing suitable for § 203 workloads.
{% endstep %}
{% endstepper %}

### UI example

In the dashboard, go to **Settings** → **Inference** and select only providers from the list of [approved providers](#approved-providers). Make sure your selection exactly matches the approved providers.

<figure><img src="https://2211217319-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FYGsEKyV2Zq4Q8fEJQT40%2Fuploads%2FR74Q4oKeSWKxOKkZsee6%2FScreenshot%202026-09-16%20at%2017.20.29.png?alt=media&amp;token=ebb0227f-51ad-4801-8a8e-713278f00bfa" alt="An example of a specific provider selection." width="563"><figcaption><p>An example of a specific provider selection. Make sure it matches approved providers.</p></figcaption></figure>

### API example

```bash
curl 'https://api.cortecs.ai/v1/chat/completions' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer <API_KEY>' \
  -d '{
    "model": "<MODEL_NAME>",
    "messages": [
      { "role": "user", "content": "<YOUR_MESSAGE>" }
    ],
    "allowed_providers": [
      "amazon_ireland",
      "amazon_paris",
      "ionos",
      "ovh",
      "aki",
      "infercom",
      "google",
      "berget",
      "tensorix"
    ]
  }'
```

When `allowed_providers` is set, Cortecs will not route or fall back to a provider outside that allowlist. If none of the listed providers can serve the request, the request fails. See [Routing Concept](/routing/routing-concept.md#parameter-handling) for more information about routing parameters.

## Approved Providers

Use the API identifiers exactly as shown or select them by name in the UI.

<table data-header-hidden data-search="false"><thead><tr><th></th><th width="170.28125"></th><th></th></tr></thead><tbody><tr><td>Name</td><td>Provider IDs</td><td>Legal entity</td></tr><tr><td>Amazon</td><td><code>amazon_ireland, amazon_paris</code></td><td>Amazon Web Services EMEA SARL</td></tr><tr><td>Ionos</td><td><code>ionos</code></td><td>IONOS SE</td></tr><tr><td>OVH</td><td><code>ovh</code></td><td>OVH SA</td></tr><tr><td>AKI</td><td><code>aki</code></td><td>AKI.IO GmbH</td></tr><tr><td>Google</td><td><code>google</code></td><td>Google Cloud EMEA Limited</td></tr><tr><td>Infercom</td><td><code>infercom</code></td><td>Infercom SCS</td></tr><tr><td>Berget</td><td><code>berget</code></td><td>Berget AI AB</td></tr><tr><td>TensorX</td><td><code>tensorix</code></td><td>TensorX Ltd</td></tr></tbody></table>

{% hint style="info" %}
Additional providers may be added to this list on a continuous basis. Customers should review this page regularly to stay informed of the current approved providers.
{% endhint %}