---
title: "Pipeline usage stats"
method: GET
path: "/stats"
tags: ["System"]
---

# Pipeline usage stats

`GET /stats`

Get cumulative LLM token usage for every pipeline

## Response `200`

Pipeline usage statistics

- StatsResponse
  - `pipelines` PipelineUsage[], required — Per-pipeline cumulative token usage
    - `completion` TokenUsage, required — Cumulative token usage since client creation or last reset
      - `cache_creation_input_tokens` integer — Cumulative tokens used to write to the prompt cache
      - `cache_read_input_tokens` integer — Cumulative tokens read from the prompt cache
      - `completion_tokens` integer, required — Cumulative completion/output tokens
      - `prompt_tokens` integer, required — Cumulative prompt/input tokens
      - `total_tokens` integer, required — Cumulative total tokens (prompt + completion)
    - `description` string — Pipeline description
    - `embedding` TokenUsage, required — Cumulative token usage since client creation or last reset
      - `cache_creation_input_tokens` integer — Cumulative tokens used to write to the prompt cache
      - `cache_read_input_tokens` integer — Cumulative tokens read from the prompt cache
      - `completion_tokens` integer, required — Cumulative completion/output tokens
      - `prompt_tokens` integer, required — Cumulative prompt/input tokens
      - `total_tokens` integer, required — Cumulative total tokens (prompt + completion)
    - `name` string, required — Pipeline name

---

[API](https://skmtc.net/pgedge/apis/pgedge-rag-server-api.md) · [All operations](https://skmtc.net/pgedge/apis/pgedge-rag-server-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/pgedge/pgedge-rag-server-api/versions/bfa21179cba1/schema)