---
title: "POST /imageanalysis:analyze"
method: POST
path: "/imageanalysis:analyze"
---

# POST /imageanalysis:analyze

`POST /imageanalysis:analyze`

Analyze the input image. The request either contains image stream with any content type ['image/*', 'application/octet-stream'], or a JSON payload which includes an url property to be used to retrieve the image stream.

## Query parameters

- `features` string[]
- `language` string
- `model-version` string
- `smartcrops-aspect-ratios` unknown[]
  - unknown
- `gender-neutral-caption` boolean
- `api-version` string, required

## Request body

- ImageUrl — A JSON document with a URL pointing to the publicly accessible image to be analyzed.
  - `url` string, uri, required — Publicly reachable URL of an image.

## Response `200`

Success

- ImageAnalysisResult — Describe the combined results of different types of image analysis.
  - `captionResult` CaptionResult — A brief description of what the image depicts.
    - `text` string, required — The text of the caption.
    - `confidence` number, double, required — The level of confidence the service has in the caption. Confidence scores span the range of 0.0 to 1.0 (inclusive), with higher values indicating a higher confidence of a match.
  - `objectsResult` ObjectsResult — Describes detected objects in an image.
    - `values` DetectedObject[], required — An array of detected objects.
      - `id` string — Id of the detected object.
      - `boundingBox` BoundingBox, required — A bounding box for an area inside an image.
        - `x` integer, required — Left-coordinate of the top left point of the area, in pixels.
        - `y` integer, required — Top-coordinate of the top left point of the area, in pixels.
        - `w` integer, required — Width measured from the top-left point of the area, in pixels.
        - `h` integer, required — Height measured from the top-left point of the area, in pixels.
      - `tags` ContentTag[], required — Classification confidences of the detected object.
        - `name` string, required — Name of the entity.
        - `confidence` number, double, required — The level of confidence that the entity was observed. Confidence scores span the range of 0.0 to 1.0 (inclusive), with higher values indicating a higher confidence of a match.
  - `readResult` ReadResult — The results of an Read operation.
    - `blocks` DetectedTextBlock[], required — A list of text blocks.
      - `lines` DetectedTextLine[], required — List of text lines in the text block.
        - `text` string, required — Text content of the detected text line.
        - `boundingPolygon` ImagePoint[], required — Bounding polygon of the text line.
          - `x` integer, required — The x-coordinate of this point.
          - `y` integer, required — The y-coordinate of this point.
        - `words` DetectedTextWord[], required — List of words in the text line.
          - `text` string, required — Text content of the word.
          - `boundingPolygon` ImagePoint[], required — Bounding polygon of the word.
            - `x` integer, required — The x-coordinate of this point.
            - `y` integer, required — The y-coordinate of this point.
          - `confidence` number, double, required — The level of confidence that the word was detected. Confidence scores span the range of 0.0 to 1.0 (inclusive), with higher values indicating a higher confidence of a match.
  - `denseCaptionsResult` DenseCaptionsResult — A list of captions.
    - `values` DenseCaption[], required — A list of captions.
      - `text` string, required — The text of the caption.
      - `confidence` number, double, required — The level of confidence the service has in the caption. Confidence scores span the range of 0.0 to 1.0 (inclusive), with higher values indicating a higher confidence of a match.
      - `boundingBox` BoundingBox — A bounding box for an area inside an image.
        - `x` integer, required — Left-coordinate of the top left point of the area, in pixels.
        - `y` integer, required — Top-coordinate of the top left point of the area, in pixels.
        - `w` integer, required — Width measured from the top-left point of the area, in pixels.
        - `h` integer, required — Height measured from the top-left point of the area, in pixels.
  - `modelVersion` string, required — Model Version.
  - `metadata` ImageMetadata, required — The image metadata information such as height and width.
    - `width` integer, required — The width of the image in pixels.
    - `height` integer, required — The height of the image in pixels.
  - `tagsResult` TagsResult — A list of tags with confidence level.
    - `values` ContentTag[], required — A list of tags with confidence level.
      - `name` string, required — Name of the entity.
      - `confidence` number, double, required — The level of confidence that the entity was observed. Confidence scores span the range of 0.0 to 1.0 (inclusive), with higher values indicating a higher confidence of a match.
  - `smartCropsResult` SmartCropsResult — Smart cropping result.
    - `values` CropRegion[], required — Recommended regions for cropping the image.
      - `aspectRatio` number, double, required — The aspect ratio of the crop region.
      - `boundingBox` BoundingBox, required — A bounding box for an area inside an image.
        - `x` integer, required — Left-coordinate of the top left point of the area, in pixels.
        - `y` integer, required — Top-coordinate of the top left point of the area, in pixels.
        - `w` integer, required — Width measured from the top-left point of the area, in pixels.
        - `h` integer, required — Height measured from the top-left point of the area, in pixels.
  - `peopleResult` PeopleResult — An object describing whether the image contains people.
    - `values` DetectedPerson[], required — An array of detected people.
      - `boundingBox` BoundingBox, required — A bounding box for an area inside an image.
        - `x` integer, required — Left-coordinate of the top left point of the area, in pixels.
        - `y` integer, required — Top-coordinate of the top left point of the area, in pixels.
        - `w` integer, required — Width measured from the top-left point of the area, in pixels.
        - `h` integer, required — Height measured from the top-left point of the area, in pixels.
      - `confidence` number, double, required — Confidence score of having observed the person in the image. Confidence scores span the range of 0.0 to 1.0 (inclusive), with higher values indicating a higher confidence of a match.

## Other responses

- `default` — Error

## Changes

- **2026-07-13** (2023-02-01-preview) `4021295051f4` — 1 warning, 2 info
  - deleted the `query` request parameter `model-name`
  - api operation id `ImageAnalysis_AnalyzeImage` removed and replaced with `Analyze_Image`
  - added the new optional `query` request parameter `model-version`
- **2023-03-07** (2023-02-01-preview) `cd3b1515d86b` — 1 warning, 3 info
  - deleted the `query` request parameter `model-version`
  - api operation id `Analyze_Image` removed and replaced with `ImageAnalysis_Analyze`
  - api tag `OperationsApi` added
  - added the new optional `query` request parameter `model-name`

[Change history](https://skmtc.dev/azure/apis/cognitiveservices-unifiedvision/changes/imageanalysis:analyze/post.md)

---

[API](https://skmtc.dev/azure/apis/cognitiveservices-unifiedvision.md) · [All operations](https://skmtc.dev/azure/apis/cognitiveservices-unifiedvision/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/azure/cognitiveservices-unifiedvision/revisions/047f04ae4b61/schema)