> ## Documentation Index > Fetch the complete documentation index at: https://docs.getlimina.ai/llms.txt > Use this file to discover all available pages before exploring further. # Prometheus metrics endpoint > This endpoint serves Prometheus metrics via a HTTP-based interface that provides access to metrics data in a format suitable for scraping by Prometheus servers. The endpoint provides real-time insights into how the system is functioning. The endpoint exposed the metrics in a time-series format, allowing you to track various types of data, including system resources usage, application performance, and other custom metrics. Currently following metrics are available: * **cpu_usage_percent** (_CPU usage in percentage._) * **cpu_memory_used_bytes** (_Used CPU memory, in bytes._) * **cpu_memory_total_bytes** (_Total CPU memory, in bytes._) * **cpu_load_percent** (_CPU load, in percentage. Calculated for last 1m, 5m & 15m._) * **http_request_size_bytes** (_HTTP request sizes in bytes grouped by method, status and handler._) * **http_requests_total** (_Total number of requests grouped by method, status and handler._) * **http_request_duration_seconds** (_Duration of HTTP requests in seconds._) * **characters_processed_total** (_Total number of characters processed._) * Triton metrics (if GPU mode is enabled and Triton server is running.) ## OpenAPI ````yaml /openapi/privateai_4.5.0.json get /metrics openapi: 3.1.0 info: title: API Reference description: Private AI API Reference termsOfService: https://www.getlimina.ai/en/terms-of-use contact: url: https://www.getlimina.ai/en/contact-us email: info@getlimina.ai version: 4.3.0 servers: - url: https://api.getlimina.ai/community/v4 description: Private AI Community API - url: https://api.getlimina.ai/professional/v4 description: Private AI Professional API - url: http://localhost:8080 description: Local Server security: [] paths: /metrics: get: summary: Prometheus metrics endpoint description: >- This endpoint serves Prometheus metrics via a HTTP-based interface that provides access to metrics data in a format suitable for scraping by Prometheus servers. The endpoint provides real-time insights into how the system is functioning. The endpoint exposed the metrics in a time-series format, allowing you to track various types of data, including system resources usage, application performance, and other custom metrics. Currently following metrics are available: * **cpu_usage_percent** (_CPU usage in percentage._) * **cpu_memory_used_bytes** (_Used CPU memory, in bytes._) * **cpu_memory_total_bytes** (_Total CPU memory, in bytes._) * **cpu_load_percent** (_CPU load, in percentage. Calculated for last 1m, 5m & 15m._) * **http_request_size_bytes** (_HTTP request sizes in bytes grouped by method, status and handler._) * **http_requests_total** (_Total number of requests grouped by method, status and handler._) * **http_request_duration_seconds** (_Duration of HTTP requests in seconds._) * **characters_processed_total** (_Total number of characters processed._) * Triton metrics (if GPU mode is enabled and Triton server is running.) operationId: metrics_endpoint_metrics_get responses: '200': description: Successful Response content: text/plain: schema: type: string example: > # HELP characters_processed_total Number of characters processed # TYPE characters_processed_total counter characters_processed_total 63.0 # HELP characters_processed_created Number of characters processed # TYPE characters_processed_created gauge characters_processed_created 1.7848166590821865e+09 # HELP http_request_duration_seconds Duration of HTTP requests in seconds # TYPE http_request_duration_seconds histogram http_request_duration_seconds_bucket{handler="/analyze/text",le="0.005",method="POST",status="2xx"} 0.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="0.01",method="POST",status="2xx"} 0.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="0.025",method="POST",status="2xx"} 0.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="0.05",method="POST",status="2xx"} 0.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="0.075",method="POST",status="2xx"} 0.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="0.1",method="POST",status="2xx"} 0.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="0.25",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="0.5",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="0.75",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="1.0",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="2.5",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="5.0",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="7.5",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="10.0",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="25.0",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="50.0",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="75.0",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="100.0",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="250.0",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="500.0",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="750.0",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="1000.0",method="POST",status="2xx"} 1.0 http_request_duration_seconds_bucket{handler="/analyze/text",le="+Inf",method="POST",status="2xx"} 1.0 http_request_duration_seconds_count{handler="/analyze/text",method="POST",status="2xx"} 1.0 http_request_duration_seconds_sum{handler="/analyze/text",method="POST",status="2xx"} 0.10682842321693897 # HELP http_request_duration_seconds_created Duration of HTTP requests in seconds # TYPE http_request_duration_seconds_created gauge http_request_duration_seconds_created{handler="/analyze/text",method="POST",status="2xx"} 1.7848166708028271e+09 # HELP http_requests_total Total number of requests by method, status and handler. # TYPE http_requests_total counter http_requests_total{handler="/analyze/text",method="POST",status="2xx"} 1.0 # HELP http_requests_created Total number of requests by method, status and handler. # TYPE http_requests_created gauge http_requests_created{handler="/analyze/text",method="POST",status="2xx"} 1.7848166708029535e+09 # HELP http_request_size_bytes Content bytes of requests. # TYPE http_request_size_bytes summary http_request_size_bytes_count{handler="/analyze/text",method="POST",status="2xx"} 1.0 http_request_size_bytes_sum{handler="/analyze/text",method="POST",status="2xx"} 81.0 # HELP http_request_size_bytes_created Content bytes of requests. # TYPE http_request_size_bytes_created gauge http_request_size_bytes_created{handler="/analyze/text",method="POST",status="2xx"} 1.78481667080302e+09 # HELP cpu_usage_percent CPU usage, in percentage # TYPE cpu_usage_percent gauge cpu_usage_percent 5.6 # HELP cpu_memory_used_bytes CPU used memory, in bytes # TYPE cpu_memory_used_bytes gauge cpu_memory_used_bytes 1.0639978496e+010 # HELP cpu_memory_total_bytes CPU total memory, in bytes # TYPE cpu_memory_total_bytes gauge cpu_memory_total_bytes 6.7361595392e+010 # HELP cpu_load_percent CPU load, in percentage. Calculated for last 1m, 5m & 15m. # TYPE cpu_load_percent gauge cpu_load_percent{duration="1m"} 2.764892578125 cpu_load_percent{duration="5m"} 1.6642252604166667 cpu_load_percent{duration="15m"} 1.409912109375 # Triton Server Metrics Examples: # HELP nv_gpu_utilization GPU utilization in percentage # TYPE nv_gpu_utilization gauge nv_gpu_utilization{gpu=0} 45.2 # HELP nv_gpu_memory_used_bytes GPU memory used in bytes # TYPE nv_gpu_memory_used_bytes gauge nv_gpu_memory_used_bytes{gpu=0} 8589934592.0 # HELP triton_inference_request_success Total number of successful requests # TYPE triton_inference_request_success counter triton_inference_request_success{model="deid_model"} 150.0 ````