---
title: "Usage Summary Csv"
method: GET
path: "/v1/usage/summary.csv"
tags: ["usage"]
---

# Usage Summary Csv

`GET /v1/usage/summary.csv`

Download the per-model / per-user / per-key breakdown as CSV.

A dedicated route rather than a ``format=csv`` flag on ``/summary`` so that
endpoint keeps a single JSON response model and a clean OpenAPI schema. The
export is **uncapped** (no top-N fold): finance wants every row. Kept separate
from the bare-array ``/v1/usage`` contract, which is untouched.

## Query parameters

- `start_date` string, date-time, nullable — Return logs with timestamp >= start_date (ISO 8601 or Unix epoch seconds)
- `end_date` string, date-time, nullable — Return logs with timestamp < end_date (ISO 8601 or Unix epoch seconds)
- `user_id` string, nullable — Filter to a single user
- `status` string, nullable — Filter to a single status (e.g. 'success' or 'error')
- `model` string, nullable — Filter to a single model
- `endpoint` string, nullable — Filter to a single endpoint (e.g. '/v1/chat/completions')

## Response `200`

Successful Response

- unknown

## Other responses

- `422` — Validation Error

## Changes

- **2026-07-21** `b58ece3074c8` — 1 info
  - endpoint added

[Change history](https://skmtc.dev/mozilla-ai/apis/otari/changes/v1/usage/summary.csv/get.md)

---

[API](https://skmtc.dev/mozilla-ai/apis/otari.md) · [All operations](https://skmtc.dev/mozilla-ai/apis/otari/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/mozilla-ai/otari/revisions/66056c7fd2e2/schema)