> ## Documentation Index
> Fetch the complete documentation index at: https://docs.voiceflow.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Sending an analytics query

> Analytics endpoints end in the level they measure. Pick organization, workspace, or project scope, then POST a body describing window and grouping.

Analytics turns conversations into numbers: how many, how long, how much they
cost, and which playbooks, functions, and tools accounted for the spend.

## Every query has a scope

Analytics endpoints end in the level they measure, and the level is part of the
path:

```text theme={null}
/v1/stable/analytics/query/token-usage/organization/{organizationID}
/v1/stable/analytics/query/token-usage/workspace/{workspaceID}
/v1/stable/analytics/query/token-usage/project/{projectID}
```

Not every metric exists at every level, which is itself informative: interaction
counts are project and workspace, entity token usage is organization only.

## What you can measure

* **Spend** - token usage overall, by hour, by day, by category, and by entity;
  plus transcript cost.
* **Volume** - interactions, transcripts, unique users, call count and call
  duration.
* **Where it goes** - usage attributed to functions, playbooks, workflows,
  intents, prompts, integrations, API tools, MCP tools and knowledge base
  documents.

That last group is the one most people skip. It answers which parts of an agent
are actually costing money, rather than what the agent cost in total.

## Sending a query

Each query takes a request body describing the window and grouping you want, so
they are `POST` rather than `GET` despite being reads.

## What analytics does not return

Analytics returns numbers about conversations, never the conversations
themselves. To read what was actually said, use
[Observe](/api-reference/sections/observe).