# Computer Vision Client API

> Computer Vision Client API on Apizie: 11 endpoints (This operation extracts a rich set of visual features based on the image content. Two input methods are…, This operation generates a description of an image in human readable language with complete sentences. The…, Performs object detection on the specified image. Two input methods are supported -- (1) Uploading an image…, This operation returns the list of domain-specific models that are supported by the Computer Vision API.…, …) 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://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/{endpoint} or from Claude, ChatGPT and Cursor through the Apizie MCP server. Free plan: 1,000 requests a month.

- Project key: `cloud:azure-cognitiveservices-computer-vision`
- Category: Cloud
- Status: byok
- Source: https://learn.microsoft.com/rest/api/azure/
- Page: https://apizie.tech/api/cloud/azure-cognitiveservices-computer-vision
- OpenAPI: https://apizie.tech/api/cloud/azure-cognitiveservices-computer-vision/openapi.json

The Computer Vision API provides state-of-the-art algorithms to process images and return information. For example, it can be used to determine if an image contains mature content, or it can be used to find all the…

## Endpoints

### This operation extracts a rich set of visual features based on the image content. Two input methods are…
`POST https://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/analyze-image` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints. |
| visualFeatures | array | no | A string indicating what visual feature types to return. Multiple values should be comma-separated. Valid visual feature types include:… |
| details | array | no | A string indicating which domain-specific details to return. Multiple values should be comma-separated. Valid visual feature types… |
| language | string | no | The desired language for output generation. If this parameter is not specified, the default value is "en". See https://aka.ms/cv-languages… |
| descriptionExclude | array | no | Turn off specified domain models when generating the description. |
| model-version | string | no | Optional parameter to specify the version of the AI model. Accepted values are: "latest", "2021-04-01", "2021-05-01". Defaults to "latest". |
| body | object | yes | JSON request body |

### This operation generates a description of an image in human readable language with complete sentences. The…
`POST https://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/describe-image` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints. |
| maxCandidates | integer | no | Maximum number of candidate descriptions to be returned. The default is 1. |
| language | string | no | The desired language for output generation. If this parameter is not specified, the default value is "en". See https://aka.ms/cv-languages… |
| descriptionExclude | array | no | Turn off specified domain models when generating the description. |
| model-version | string | no | Optional parameter to specify the version of the AI model. Accepted values are: "latest", "2021-04-01", "2021-05-01". Defaults to "latest". |
| body | object | yes | JSON request body |

### Performs object detection on the specified image. Two input methods are supported -- (1) Uploading an image…
`POST https://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/detect-objects` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints. |
| model-version | string | no | Optional parameter to specify the version of the AI model. Accepted values are: "latest", "2021-04-01", "2021-05-01". Defaults to "latest". |
| body | object | yes | JSON request body |

### This operation returns the list of domain-specific models that are supported by the Computer Vision API.…
`GET https://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/list-models` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints. |

### This operation recognizes content within an image by applying a domain-specific model. The list of…
`POST https://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/analyze-image-by-domain` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints. |
| model | string | yes | The domain-specific content to recognize. |
| language | string | no | The desired language for output generation. If this parameter is not specified, the default value is "en". See https://aka.ms/cv-languages… |
| model-version | string | no | Optional parameter to specify the version of the AI model. Accepted values are: "latest", "2021-04-01", "2021-05-01". Defaults to "latest". |
| body | object | yes | JSON request body |

### Optical Character Recognition (OCR) detects text in an image and extracts the recognized characters into a…
`POST https://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/recognize-printed-text` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints. |
| detectOrientation | boolean | yes | Whether detect the text orientation in the image. With detectOrientation=true the OCR service tries to detect the image orientation and… |
| language | string | no | The BCP-47 language code of the text to be detected in the image. The default value is 'unk'. |
| model-version | string | no | Optional parameter to specify the version of the AI model. Accepted values are: "latest", "2021-04-01", "2021-05-01". Defaults to "latest". |
| body | object | yes | JSON request body |

### This operation generates a list of words, or tags, that are relevant to the content of the supplied image.…
`POST https://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/tag-image` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints. |
| language | string | no | The desired language for output generation. If this parameter is not specified, the default value is "en". See https://aka.ms/cv-languages… |
| model-version | string | no | Optional parameter to specify the version of the AI model. Accepted values are: "latest", "2021-04-01", "2021-05-01". Defaults to "latest". |
| body | object | yes | JSON request body |

### This operation generates a thumbnail image with the user-specified width and height. By default, the service…
`POST https://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/generate-thumbnail` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints. |
| width | integer | yes | Width of the thumbnail, in pixels. It must be between 1 and 1024. Recommended minimum of 50. |
| height | integer | yes | Height of the thumbnail, in pixels. It must be between 1 and 1024. Recommended minimum of 50. |
| smartCropping | boolean | no | Boolean flag for enabling smart cropping. |
| model-version | string | no | Optional parameter to specify the version of the AI model. Accepted values are: "latest", "2021-04-01", "2021-05-01". Defaults to "latest". |
| body | object | yes | JSON request body |

### This operation returns a bounding box around the most important area of the image. A successful response…
`POST https://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/get-area-of-interest` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints. |
| model-version | string | no | Optional parameter to specify the version of the AI model. Accepted values are: "latest", "2021-04-01", "2021-05-01". Defaults to "latest". |
| body | object | yes | JSON request body |

### Use this interface to get the result of a Read operation, employing the state-of-the-art Optical Character…
`POST https://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/read` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints. |
| language | string | no | The BCP-47 language code of the text in the document. Read supports auto language identification and multi-language documents, so only… |
| pages | array | no | Custom page numbers for multi-page documents(PDF/TIFF), input the number of the pages you want to get OCR result. For a range of pages,… |
| model-version | string | no | Optional parameter to specify the version of the OCR model used for text extraction. Accepted values are: "latest", "latest-preview",… |
| readingOrder | string | no | Optional parameter to specify which reading order algorithm should be applied when ordering the extract text elements. Can be either… |
| body | object | yes | JSON request body |

### This interface is used for getting OCR results of Read operation. The URL to this interface should be…
`GET https://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/get-read-result` (byok)

| Parameter | Type | Required | Description |
|---|---|---|---|
| Endpoint | string | yes | Supported Cognitive Services endpoints. |
| operationId | string | yes | Id of read operation returned in the response of the 'Read' interface. |

## Example
```
curl "https://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/analyze-image" \
  -H "x-api-key: $APIZIE_KEY" \
  -H "x-upstream-key: $PROVIDER_KEY"
```

## FAQ

### How do I call the Computer Vision Client API?
Create a free Apizie key, then send POST https://apizie.tech/v1/cloud:azure-cognitiveservices-computer-vision/analyze-image with the header x-api-key. Every endpoint returns { project, data, timestamp }.

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

### Can AI agents use the Computer Vision Client API?
Yes. Add the Apizie MCP server (https://apizie.tech/mcp) to Claude, ChatGPT, Cursor or VS Code, then ask in plain language. The agent calls run_scraper with project key cloud:azure-cognitiveservices-computer-vision.

### What is the status of the Computer Vision Client API?
Needs your own provider key (bring your own key)