---
title: "Trigger Llm Proxy Import"
method: POST
path: "/developer/llm-proxy-requests/import"
tags: ["Developer", "Developer - LLM Proxy"]
---

# Trigger Llm Proxy Import

`POST /developer/llm-proxy-requests/import`

## Request

- Base URL: `https://api.openintake.ai` (the document declares no server; this is the origin it was published from)
- URL: `https://api.openintake.ai/developer/llm-proxy-requests/import`
- Auth: none declared

Enqueue an import. With a ``start`` this dispatches the backfill task, which
never touches the watermark; without one it runs the scheduled windowed import.

## Request body

- LLMProxyImportRequest: Trigger an import. A range dispatches the backfill task instead of the scheduled importer, so it can never rewind or skip the watermark.
  - `start` string, date-time, nullable: Backfill range start (UTC); omit to run the scheduled windowed import
  - `end` string, date-time, nullable: Backfill range end (UTC); defaults to now
  - `lookback_minutes` integer, nullable: Override the scheduled importer's start, ignoring the watermark

## Response `202`

Successful Response

- LLMProxyImportResponse
  - `message` string, required: Status message
  - `task_id` string, required: Celery task ID
  - `mode` string, required: "scheduled" or "backfill"

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/openintake/apis/openintake-api.md) - [All operations](https://skmtc.dev/openintake/apis/openintake-api/llms.txt) - [OpenAPI document](https://skmtc.dev/openintake/apis/openintake-api/revisions/de90a8dcbc07?raw)