Logging
Get Application Logs
Retrieve application logs with filtering, search, and pagination. Supports filtering by provider, model, status, time range, latency, tokens, and content search.
get/api/logs
Query parameters
providersstring
Comma-separated list of providers to filter by
modelsstring
Comma-separated list of models to filter by
statusstring
Comma-separated list of statuses to filter by (success, error)
objectsstring
Comma-separated list of object types to filter by (chat.completion, text.completion)
start_timestring date-time
Start time for filtering (RFC3339 format)
end_timestring date-time
End time for filtering (RFC3339 format)
min_latencynumber
Minimum latency in seconds
max_latencynumber
Maximum latency in seconds
min_tokensinteger
Minimum token count
max_tokensinteger
Maximum token count
content_searchstring
Search term for message content
limitinteger
Number of logs to return (1-1000)
offsetinteger
Number of logs to skip
Response
Application logs
Example response
{
"logs": [
{
"id": "log_123",
"timestamp": "2023-12-01T10:30:00Z",
"level": "info",
"message": "Request completed successfully",
"provider": "openai",
"model": "gpt-4o",
"status": "success",
"latency": 1.234,
"tokens": 87,
"object": "chat.completion"
}
],
"total": 156,
"limit": 50
}