> See the full index of documentation pages at https://docs.zettabyte.com/llms.txt.

# Call your endpoint

> Send requests to a deployed inference endpoint over HTTP.

Source: https://docs.zettabyte.com/docs/zcloud/deploy-and-serve/call-your-endpoint

Last updated: 2026-11-05

Once an endpoint is running, you can send inference requests to it over HTTP. For the full request and response reference, see [Inference API](https://docs.zettabyte.com/docs/zcloud/inference-api/inference-api).

## Before you begin

- A deployed endpoint that is running: open [**Inference**](https://console.zettabyte.com/task-inference/index) and check that its Scaling shows every replica running, for example `1/1`. See [Deploy a model](https://docs.zettabyte.com/docs/zcloud/deploy-and-serve/deploy-a-model).
- An API key. The key is shown once at creation, so copy it then. See [API keys](https://docs.zettabyte.com/docs/accounts-and-roles/api-keys).

## Find your details

You need three things:

- Your API key: in **API Keys**, select **Create API Keys**.
- Your tenant ID, shown with your tenant name in the menu at the bottom left of the sidebar.
- The endpoint's job alias name: open [**Inference**](https://console.zettabyte.com/task-inference/index) and read it from the list.

The tenant ID and job alias name combine into the `Service-Name` header, described below.

## Call with cURL

```bash
curl https://api.zettabyte.com/v1/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Service-Name: TENANT_ID.JOB_ALIAS_NAME" \
  -d '{
    "prompt": "Hello",
    "max_tokens": 128,
    "temperature": 0.7
  }'
```

## Call with Python

```python
import requests

resp = requests.post(
    "https://api.zettabyte.com/v1/completions",
    headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer YOUR_API_KEY",
        "Service-Name": "TENANT_ID.JOB_ALIAS_NAME",
    },
    json={"prompt": "Hello", "max_tokens": 128, "temperature": 0.7},
)
print(resp.json())
```

## The Service-Name header

The `Service-Name` header routes your request to your specific deployment. It is built as `TENANT_ID.JOB_ALIAS_NAME`: your tenant ID, a dot, then the endpoint's job alias name.

> [!WARNING]
> **zCLOUD-specific header**
> `Service-Name` is a zCLOUD-specific (non-standard) header. It is not part of the standard OpenAI-style API, so remember to add it **explicitly in every client**.

## Troubleshooting

- `401` or auth error: the API key has expired.
- `404` or wrong service: the `Service-Name` header is malformed. Check that it reads `TENANT_ID.JOB_ALIAS_NAME`.

## Next steps

- [Inference API](https://docs.zettabyte.com/docs/zcloud/inference-api/inference-api): the full request and response reference.
