---
title: "Per-round token use for one run"
method: GET
path: "/v1/admin/runs/{run_id}/rounds"
tags: ["admin"]
---

# Per-round token use for one run

`GET /v1/admin/runs/{run_id}/rounds`

## Request

- Base URL: `https://api.patricia.app` (the document declares no server; this is the origin it was published from)
- URL: `https://api.patricia.app/v1/admin/runs/{run_id}/rounds`
- Auth: HTTP bearer

The run's stored per-round model usage, in round order: model, uncached input, cache read, cache write and output tokens, an estimated cost in micro US dollars at current prices, which is not the recorded charge, and the prompt record (call kind, whether it was the final call, and the names and sizes of the system blocks). The estimate is empty for a model the price list does not know. `rounds_used` counts metered agent rounds when available; a null value means the count is unknown. `complete` is false when the history kept fewer rounds than `rounds_used`, because it keeps the first 1,024. Auxiliary model calls are not rounds and are not listed. No prompt or message text is returned.

## Path parameters

- `run_id` string, uuid, required: The run id.

## Response `200`

Successful Response

- RunRounds
  - `rounds_used` integer, nullable, required
  - `complete` boolean, required
  - `rounds` RunRound[], required
    - `round` integer, required
    - `model` string, nullable, required
    - `input_tokens` integer, required
    - `cache_read_tokens` integer, required
    - `cache_write_tokens` integer, required
    - `output_tokens` integer, required
    - `estimated_cost_micro_usd` integer, nullable, required
    - `prompt` object, nullable, required

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/patricia/apis/patricia-api.md) · [All operations](https://skmtc.dev/patricia/apis/patricia-api/llms.txt) · [OpenAPI document](https://skmtc.dev/patricia/apis/patricia-api/revisions/0dfb44495ea1?raw)