Skip to main content
Debug mode gives you full visibility into each request flowing through the AI Gateway: the exact messages sent to the provider, the compressed version (if compression was applied), all HTTP headers, and the raw response. This is useful for verifying compression output, diagnosing errors, and understanding exactly what your application is sending.

​
Enable debug mode on an API key

Debug logs are opt-in per API key. By default, Edgee does not store request or response bodies. Enabling debug mode tells the gateway to capture and temporarily retain the full payload for that key. Navigate to API Keys in the console sidebar. In the table, find the Debug column. Click the OFF badge for the key you want to inspect. A confirmation dialog will appear:
When debug mode is enabled, full request and response data (including headers, message bodies, and model outputs) is logged and stored temporarily. This data may contain sensitive or personal information and is accessible to all members of your organization. Enable it only when actively debugging.
Click Enable Debug Mode to confirm. The badge turns ON (green). To stop capturing debug logs, click the badge again — disabling does not require confirmation.

​
View the debug dialog

Once debug mode is on, every request made with that API key will have a bug icon available in the Logs page. Go to Logs in the console sidebar. Each row in the request table represents one LLM call. For requests captured with debug mode, click the bug icon in the rightmost column to open the debug dialog.
Logs table with debug icon

​
What the debug dialog shows

The dialog opens with full details about that specific request.

​
Metadata

A 3-column grid at the top shows at a glance:
FieldDescription
ProviderThe LLM provider the request was routed to (e.g. Anthropic, OpenAI)
ModelThe model identifier used
DurationTotal end-to-end response time
StreamingWhether the request used streaming
TimestampExact time the request was received
Key IDThe API key that made the request

​
HTTP Request

The HTTP Request section (collapsible, open by default) shows everything Edgee sent to the provider. It is organized in tabs:
  • Full Body — The complete request body as an interactive JSON tree. You can expand/collapse nodes, switch to raw JSON view, and copy the content.
  • Headers — All request headers in a key/value table. Sensitive values (such as authorization tokens) are displayed as [REDACTED].
  • Messages — The input messages array extracted from the body.
  • Compressed — The compressed version of the messages, shown only when token compression was applied to this request.
  • Compare — A side-by-side diff of the original and compressed messages. Each row corresponds to one message by index, so you can see exactly what was changed, shortened, or removed by the compression engine.
The Compare tab is the fastest way to audit compression quality: you can verify that the semantic meaning of each message was preserved before sending it to the provider.

​
Output

The Output section (collapsible, open by default) shows what the provider returned:
  • Output (Response) — The full response body for non-streaming requests, as an interactive JSON tree.
  • Output (Accumulated Content) — The concatenated streamed content for streaming requests.
  • Output (Error) — The raw error message in red if the provider returned an error or the request failed.

​
Request ID

The dialog footer displays the request ID in monospace. Use the Copy button to copy it — useful when filing a support ticket or correlating logs with your application code.

​
Compression comparison in practice

When agentic compression or Claude compression is active, the Compare tab lets you validate what was actually sent:
  1. Original message in the left column
  2. Compressed message in the right column
  3. Messages without a counterpart (e.g. if the array lengths differ) show a dash
This is the most direct way to confirm that compression preserved your instructions and that the fallback to the original prompt (triggered when the BERT score is below the semantic threshold) did or did not apply.

​
Debug log retention

Debug logs are stored temporarily and deleted automatically. They are not included in your usage exports and are not accessible via the API. If you need to preserve a specific request for later analysis, copy the full body or response JSON using the copy buttons inside the dialog.