> ## Documentation Index
> Fetch the complete documentation index at: https://docs-vip.apigo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Request IDs

> Use x-apigo-request-id to correlate client requests, ApiGo call records, and troubleshooting data.

ApiGo returns `x-apigo-request-id` in the response headers for every model request that generates a usage record. This ID links the response to the corresponding request record in ApiGo.

When a response includes this header, store it with your request data and logs. You can later use the ID to find the corresponding usage record or help ApiGo support investigate a problem.

## Read the request ID

The request ID is available in the HTTP response headers:

```http theme={null}
HTTP/1.1 200 OK
content-type: application/json
x-apigo-request-id: 2012345678901234567
```

Record it together with:

* your application request ID
* `x-apigo-request-id`
* the request time and endpoint
* the HTTP status

## Streaming requests

Streaming requests send their HTTP response headers before the data stream begins. If the response includes `x-apigo-request-id`, retain the value while reading the SSE events and associate it with the entire stream.

## Usage guidance

* Store the request ID as an opaque string. Do not convert it to a JavaScript `Number`.
* Do not parse the request ID, depend on its format, or generate it yourself.
* Do not use the request ID to determine whether a call succeeded. Use the HTTP status and response content.
* When contacting support, include the request ID, request time, endpoint, and HTTP status.

Requests rejected before ApiGo creates a usage record are outside this guarantee. This includes some gateway-level checks and early validation failures. Your client should not treat a missing request ID as a separate request failure.
