---
title: "Per-model prompt-cache usage and cost"
method: GET
path: "/v1/analytics/model-router/cache/savings"
tags: ["analytics"]
---

# Per-model prompt-cache usage and cost

`GET /v1/analytics/model-router/cache/savings`

## Query parameters

- `agent_id` string, uuid, nullable
- `operation` string, nullable
- `limit` integer
- `start_date` string, date, required
- `end_date` string, date, required

## Response `200`

Successful Response

- CacheSavingsRow[]
  - `served_model` string, required
  - `provider` string, nullable
  - `cache_read_tokens` integer, required
  - `cache_write_tokens` integer, required
  - `cache_cost_usd` number, required
  - `cache_savings_usd` number, required
  - `input_cost_usd` number, required
  - `total_cost_usd` number, required
  - `invocations` integer, required
  - `cache_hit_rate` number, required

## Other responses

- `400` — Bad request
- `401` — Authentication required
- `422` — Validation Error

## Changes

- **2026-08-12** `5a5597ebb2d6` — 1 info
  - endpoint added

[Change history](https://skmtc.dev/oneloop-hq/apis/feather-api/changes/v1/analytics/model-router/cache/savings/get.md)

---

[API](https://skmtc.dev/oneloop-hq/apis/feather-api.md) · [All operations](https://skmtc.dev/oneloop-hq/apis/feather-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/oneloop-hq/feather-api/revisions/9cd7291d4228/schema)