---
title: "POST /v1/extract/{model}"
method: POST
path: "/v1/extract/{model}"
tags: ["inference"]
---

# POST /v1/extract/{model}

`POST /v1/extract/{model}`

Successful extract work results may carry an aligned per-item error alongside partial data. Transport-level mixed failures retain generic batch behavior: the 200 response includes only successful work results.

## Path parameters

- `model` string, required

## Headers

- `X-SIE-MACHINE-PROFILE` string, nullable
- `X-SIE-Pool` string, nullable
- `X-SIE-SDK-Version` string, nullable

## Request body

- ExtractRequest
  - `items` ItemInput[], required
    - `document` DocumentInput
      - `data` integer[], required
      - `format` string, nullable
    - `id` string, nullable
    - `images` ImageInput[], nullable
      - `data` integer[], required
      - `format` string, nullable
    - `metadata` unknown
    - `text` string, nullable
  - `params` ExtractParams
    - `instruction` string, nullable
    - `labels` string[], nullable
    - `options` unknown
    - `output_schema` unknown

## Response `200`

Extract response

- ExtractResponse
  - `items` ExtractResult[], required
    - `classifications` unknown[]
      - unknown
    - `data` unknown
    - `entities` Entity[]
      - `bbox` number[], nullable
      - `end` integer, nullable
      - `label` string, required
      - `score` number, double, required
      - `start` integer, nullable
      - `text` string, required
    - `error` ExtractItemError
      - `code` string, required
      - `message` string, required
    - `id` string, required
    - `relations` Relation[]
      - `head` string, required
      - `relation` string, required
      - `score` number, double, required
      - `tail` string, required
  - `model` string, required

## Other responses

- `400` — Invalid request
- `401` — Missing or invalid bearer token
- `404` — Model not found
- `409` — Bundle override conflicts with model routing
- `413` — Request body too large
- `500` — All batch items failed or gateway internal error; gateway auth enabled but no tokens configured
- `502` — Terminal model load failure (MODEL_LOAD_FAILED)
- `503` — Provisioning in progress, queue unavailable, GPU not configured, model loading, or capacity exhausted
- `504` — Result channel closed

---

[API](https://skmtc.net/superlinked/apis/sie-gateway.md) · [All operations](https://skmtc.net/superlinked/apis/sie-gateway/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/superlinked/sie-gateway/versions/06a326e2c3e9/schema)