---
title: "Create a batch"
method: POST
path: "/v1/batches"
tags: ["Gateway"]
---

# Create a batch

`POST /v1/batches`

## Request

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

OpenAI-compatible. Runs many completions offline from an uploaded file, at a lower rate than live traffic. Only models whose `roar_batch` is true are accepted — check `GET /v1/models`. Requires `inference`.

## Response `200`

The queued batch

## Other responses

- `400`: Bad file, or a model that does not accept batches
- `401`: Missing or invalid key

---

[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)