---
title: "One batch"
method: GET
path: "/v1/batches/{id}"
tags: ["Gateway"]
---

# One batch

`GET /v1/batches/{id}`

## Request

- Base URL: `https://api.roar-ai.com`
- URL: `https://api.roar-ai.com/v1/batches/{id}`
- Auth: HTTP bearer

Status and counts for a batch. THIS is the polling endpoint, and it spends the same request-rate allowance as inference — a client that polls hard has less of its minute left for model calls, which is the trade-off to make knowingly. Requires `inference`.

## Path parameters

- `id` string, uuid, required

## Response `200`

The batch

## Other responses

- `401`: Missing or invalid key
- `404`: No such batch

---

[API](https://skmtc.dev/roar-ai/apis/roar-ai-api.md) · [All operations](https://skmtc.dev/roar-ai/apis/roar-ai-api/llms.txt) · [OpenAPI document](https://skmtc.dev/roar-ai/apis/roar-ai-api/revisions/37e4d0d5a7fe?raw)