---
title: "POST /documentModels:build"
method: POST
path: "/documentModels:build"
---

# POST /documentModels:build

`POST /documentModels:build`

Builds a custom document analysis model.

## Query parameters

- `api-version` string, required

## Request body

- BuildDocumentModelRequest — Request body to build a new custom document model.
  - `modelId` string, required — Unique document model name.
  - `description` string — Document model description.
  - `buildMode` 'template' | 'neural', required — Custom document model build mode.
  - `azureBlobSource` AzureBlobContentSource — Azure Blob Storage content.
    - `containerUrl` string, uri, required — Azure Blob Storage container URL.
    - `prefix` string — Blob name prefix.
  - `azureBlobFileListSource` AzureBlobFileListContentSource — File list in Azure Blob Storage.
    - `containerUrl` string, uri, required — Azure Blob Storage container URL.
    - `fileList` string, required — Path to a JSONL file within the container specifying a subset of documents.
  - `tags` object — List of key-value tag attributes associated with the document model.
  - `maxTrainingHours` number, float — Max number of V100-equivalent GPU hours to use for model training. Default=0.5.
  - `allowOverwrite` boolean — Allow overwriting an existing model with the same name.

## Response `202`

The request has been accepted for processing, but processing has not yet completed.

## Other responses

- `default` — An unexpected error response.

---

[API](https://skmtc.net/azure/apis/ai-documentintelligence.md) · [All operations](https://skmtc.net/azure/apis/ai-documentintelligence/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/azure/ai-documentintelligence/versions/3f750834da9e/schema)