Skip to main content
GET
/
serverless
/
metrics
Metrics
curl --request GET \
  --url https://api.fal.ai/v1/serverless/metrics \
  --header 'Authorization: <api-key>'
"# HELP fal_app_runners Number of fal app runners\n# TYPE fal_app_runners gauge\nfal_app_runners{application=\"my/app\",machine_type=\"NVIDIA B200\",state=\"running\"} 21\n# HELP fal_app_queue_size Current size of the fal app queue\n# TYPE fal_app_queue_size gauge\nfal_app_queue_size{application=\"my/app\"} 7\n# HELP fal_app_concurrent_requests Current number of concurrent requests being processed\n# TYPE fal_app_concurrent_requests gauge\nfal_app_concurrent_requests{application=\"my/app\"} 3\n# HELP fal_app_requests_completed Number of requests completed in the last minute\n# TYPE fal_app_requests_completed gauge\nfal_app_requests_completed{application=\"my/app\",method=\"POST\",status=\"200\"} 18\n# HELP fal_app_requests_received Number of requests received in the last minute\n# TYPE fal_app_requests_received gauge\nfal_app_requests_received{application=\"my/app\",method=\"POST\"} 24\n# HELP fal_app_request_latency Number of requests completed, bucketed by latency in seconds\n# TYPE fal_app_request_latency gauge\nfal_app_request_latency{application=\"my/app\",le=\"1.0\"} 5\nfal_app_request_latency{application=\"my/app\",le=\"+Inf\"} 24"

Documentation Index

Fetch the complete documentation index at: https://fal.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

API key must be prefixed with "Key ", e.g. Authorization: Key YOUR_API_KEY

Response

Prometheus-compatible metrics retrieved successfully

Prometheus-compatible metrics in text format

Example:

"# HELP fal_app_queue_size Current size of the fal app queue\n# TYPE fal_app_queue_size gauge\nfal_requests_total{application=\"my/app\"} 10"