Metrics

curl --request GET \
  --url https://api.fal.ai/v1/serverless/metrics \
  --header 'Authorization: <api-key>'

import requests

url = "https://api.fal.ai/v1/serverless/metrics"

headers = {"Authorization": "<api-key>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: '<api-key>'}};

fetch('https://api.fal.ai/v1/serverless/metrics', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

# HELP fal_app_runners Number of fal app runners
# TYPE fal_app_runners gauge
fal_app_runners{application="my/app",machine_type="NVIDIA B200",state="running"} 21
# HELP fal_app_queue_size Current size of the fal app queue
# TYPE fal_app_queue_size gauge
fal_app_queue_size{application="my/app"} 7
# HELP fal_app_concurrent_requests Current number of concurrent requests being processed
# TYPE fal_app_concurrent_requests gauge
fal_app_concurrent_requests{application="my/app"} 3
# HELP fal_app_requests_completed Number of requests completed in the last minute
# TYPE fal_app_requests_completed gauge
fal_app_requests_completed{application="my/app",method="POST",status="200"} 18
# HELP fal_app_requests_received Number of requests received in the last minute
# TYPE fal_app_requests_received gauge
fal_app_requests_received{application="my/app",method="POST"} 24
# HELP fal_app_request_latency Number of requests completed, bucketed by latency in seconds
# TYPE fal_app_request_latency gauge
fal_app_request_latency{application="my/app",le="1.0"} 5
fal_app_request_latency{application="my/app",le="+Inf"} 24

{
  "error": {
    "type": "authorization_error",
    "message": "Authentication required"
  }
}

{
  "error": {
    "type": "rate_limited",
    "message": "Rate limit exceeded"
  }
}

{
  "error": {
    "type": "server_error",
    "message": "An unexpected error occurred"
  }
}