# Alibaba Cloud DocumentAutoMind API

> Alibaba Cloud DocumentAutoMind API on Apizie: 7 endpoints (Creates an asynchronous prediction task for document self-learning, Performs model prediction in three types: long document information extraction, single receipt information…, Performs prediction using the document self-learning classifier, Performs model prediction, which includes three types: long document information extraction, single receipt…, …) returned as clean JSON through one API key. Send your own provider key in the x-upstream-key header. Call it over REST at https://zieapi.vercel.app/v1/cloud:aliyun-documentautoml/{endpoint} or from Claude, ChatGPT and Cursor through the Apizie MCP server. Free plan: 1,000 requests a month.

- Project key: `cloud:aliyun-documentautoml`
- Category: Cloud
- Status: byok
- Source: https://api.alibabacloud.com/product/documentautoml
- Page: https://zieapi.vercel.app/api/cloud/aliyun-documentautoml
- OpenAPI: https://zieapi.vercel.app/api/cloud/aliyun-documentautoml/openapi.json

Alibaba Cloud OpenAPI for DocumentAutoMind (documentautoml, version 2022-12-29). Calls are signed with ACS3-HMAC-SHA256 using your AccessKey ID and secret.

## Endpoints

### Creates an asynchronous prediction task for document self-learning
`POST https://zieapi.vercel.app/v1/cloud:aliyun-documentautoml/create-model-async-predict` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| endpoint | string | no | Regional endpoint, for example https://documentautoml.cn-beijing.aliyuncs.com |
| ModelVersion | string | no | The version number of the model. If this parameter is not specified, the latest active version of the model is used by default |
| BinaryToText | string | no | Set to false when the content field contains an image URL. Set to true when the body contains Base64-encoded content |
| Content | string | no | The URL of the image or PDF file |
| ModelId | integer | no | The model ID. You can obtain the model ID from the model list page |
| ServiceName | string | no | The service name of the pre-training service |
| ServiceVersion | string | no | The version of the pre-trained service |
| Body | string | no | The Base64 encoding content of the image |

### Performs model prediction in three types: long document information extraction, single receipt information…
`POST https://zieapi.vercel.app/v1/cloud:aliyun-documentautoml/get-model-async-predict` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| endpoint | string | no | Regional endpoint, for example https://documentautoml.cn-beijing.aliyuncs.com |
| AsyncPredictId | integer | yes | The unique ID of the asynchronous prediction. This ID is used to query the asynchronous prediction result |

### Performs prediction using the document self-learning classifier
`POST https://zieapi.vercel.app/v1/cloud:aliyun-documentautoml/predict-classifier-model` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| endpoint | string | no | Regional endpoint, for example https://documentautoml.cn-beijing.aliyuncs.com |
| ClassifierId | integer | no | The classifier ID |
| AutoPrediction | string | no | Specifies whether to enable automatic prediction. Valid values: false: Disabled. true: Enabled. Default value: true |
| Content | string | no | The accessible URL of an image or PDF file |
| Body | string | no | The Base64 encoding content of the image |
| BinaryToText | string | no | Specifies whether the input is Base64-encoded content. Set this parameter to false when the Content field is an image URL. Set this… |

### Performs model prediction, which includes three types: long document information extraction, single receipt…
`POST https://zieapi.vercel.app/v1/cloud:aliyun-documentautoml/predict-model` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| endpoint | string | no | Regional endpoint, for example https://documentautoml.cn-beijing.aliyuncs.com |
| Content | string | no | The URL for accessing the image or PDF file |
| ModelVersion | string | no | The version number of the model. If this parameter is not specified, the latest effective version of the model is used by default |
| ModelId | integer | yes | The model ID. You can obtain the model ID from the model list page |
| BinaryToText | string | no | Set to false when the Content field contains an image URL. Set to true when the Body field contains Base64-encoded content |
| Body | string | no | The Base64 encoding content of the image |

### Provides preset capability predictions. Currently available: UIE extraction, applicable to general-purpose…
`POST https://zieapi.vercel.app/v1/cloud:aliyun-documentautoml/predict-pre-train-model` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| endpoint | string | no | Regional endpoint, for example https://documentautoml.cn-beijing.aliyuncs.com |
| Content | string | no | The prediction content in JSON string format. UIE extraction parameter format: {"query":"xxx","schema":["field1","field2"]}. query… |
| ServiceVersion | string | no | The version of the preset capability service. Default value: V1 |
| ServiceName | string | no | The service name of the preset capability service. This parameter is required. For UIE extraction, set this parameter to "FormUIE" |
| BinaryToText | string | no | Set to false when the Content field contains an image URL. Set to true when the Body field contains a Base64-encoded image |
| Body | string | no | The prediction content when passing a Base64-encoded image, in JSON character string format. UIE extraction parameter format:… |

### Performs template-based prediction, which currently includes two types: custom KV templates and custom table…
`POST https://zieapi.vercel.app/v1/cloud:aliyun-documentautoml/predict-template-model` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| endpoint | string | no | Regional endpoint, for example https://documentautoml.cn-beijing.aliyuncs.com |
| TaskId | integer | yes | The task ID |
| Content | string | no | The URL of the image or PDF file |
| BinaryToText | string | no | Set to false when the Content field contains an image URL. Set to true when the Body field contains Base64-encoded content |
| Body | string | no | The Base64 encoding content of the image |

### version
`POST https://zieapi.vercel.app/v1/cloud:aliyun-documentautoml/version` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| endpoint | string | no | Regional endpoint, for example https://documentautoml.cn-beijing.aliyuncs.com |

## Example
```
curl "https://zieapi.vercel.app/v1/cloud:aliyun-documentautoml/create-model-async-predict" \
  -H "x-api-key: $APIZIE_KEY" \
  -H "x-upstream-key: $PROVIDER_KEY"
```

## FAQ

### How do I call the Alibaba Cloud DocumentAutoMind API?
Create a free Apizie key, then send POST https://zieapi.vercel.app/v1/cloud:aliyun-documentautoml/create-model-async-predict with the header x-api-key. Every endpoint returns { project, data, timestamp }.

### Is the Alibaba Cloud DocumentAutoMind API free on Apizie?
Yes. The Free plan includes 1,000 requests a month at 100 requests a minute, no credit card. Alibaba Cloud DocumentAutoMind itself also needs your own key from aliyuncs.com.

### Can AI agents use the Alibaba Cloud DocumentAutoMind API?
Yes. Add the Apizie MCP server (https://zieapi.vercel.app/mcp) to Claude, ChatGPT, Cursor or VS Code, then ask in plain language. The agent calls run_scraper with project key cloud:aliyun-documentautoml.

### What is the status of the Alibaba Cloud DocumentAutoMind API?
Needs your own provider key (bring your own key)