Request Logs

Browse and export your individual AI requests

The Logs page shows every individual request that passed through the Metrion proxy. Where the dashboard shows aggregated charts and summaries, Logs gives you the raw record — one row per request, with full detail on tokens, cost, latency, and status.

Columns

Column	Description
Status	HTTP response code, color-coded: green (2xx), orange (4xx), red (5xx). A Cached badge appears if the response was served from cache.
Timestamp	Date and time of the request
Requester	The value of the x-metrion-user header, if present
Model	The AI model that handled the request
Provider	The provider (Anthropic, OpenAI, Gemini, Mistral, Grok)
Input tokens	Tokens sent in the request
Output tokens	Tokens returned in the response
Total tokens	Sum of input and output tokens
Cost	Estimated cost in USD
Latency	Round-trip time measured by the proxy in milliseconds

The Requester column only appears when at least one request in the current page has an x-metrion-user value.

The Requester column displays the value you pass in the x-metrion-user header. This header is optional — if you don’t send it, the column is hidden. Add it to your requests to track usage by team member, application, or agent. For example: x-metrion-user: invoice-bot.

Pagination

Logs are paginated at 50 requests per page. Use the Previous and Next buttons at the bottom of the table to navigate. The total request count for the current filter is shown in the footer.

Search

A search bar at the top of the table lets you filter the current page by model name or requester. Type any partial string — the filter applies immediately as you type.

Advanced filters

Click Filters to open the same filter panel available on the dashboard. Filters apply server-side and update the full result set (not just the current page):

Filter	Description
Model	Select one or more specific models
Provider	Filter by provider
HTTP status	Filter to specific response status codes
Requester	Filter by x-metrion-user value
Cost range	Minimum and/or maximum cost per request
Token range	Minimum and/or maximum token count per request

Active filters persist in the URL, so you can bookmark or share a filtered view.

History

Plan	Log retention
Free	7 days
Pro	90 days

CSV export

CSV export is a Pro-only feature. On the Free plan, the export button is replaced with an upgrade prompt. Upgrade to Pro to download your full log history as a CSV file.

On Pro, click Export CSV to download all logs matching your current filters as a .csv file. The export follows RFC 4180 formatting and includes all columns available in the table.