This topic describes the billable items of Intelligent Media Management (IMM).
International site billable item pricing
Major billable items in Intelligent Media Management (IMM) are related to image intelligence, metadata management, media management, document processing, and file processing.
Starting from 11:00 on July 28, 2025 (UTC+8), IMM will start charging for some previously free features and adjust prices for some existing billable items. For more information, see IMM Pricing Adjustment Announcement .
Image intelligence
The following table describes billable items in the image intelligence category.
Billable item | Description | Related API operations | Related x-oss-process operations | Price before 11:00 on July 28, 2025 (USD) | Price after 11:00 on July 28, 2025 (USD) | Unit |
ImageDetect | Face detection | DetectImageFaces | image/faces | 0.028 | 0.028 | 1,000 calls |
Human detection | DetectImageBodies | image/bodies | Available free of charge for a limited period of time | |||
Vehicle detection | DetectImageCars | image/cars | Available free of charge for a limited period of time | |||
ImageLabel | Image label | DetectImageLabels | image/labels | 0.142 | 0.142 | 1,000 calls |
ImageInsight | Face search |
| Available free of charge for a limited period of time | 0.028 | 1,000 calls | |
Face Image Basics |
|
| 0.028 | |||
ImageFaceClustering | Face clustering |
| 7.0754717 | 7.0754717 | 1,000 calls | |
GenerateStory | Story generation | CreateStory | 7.0754717 | 7.0754717 | 1,000 calls | |
ImageMosaic | Image pixelation | AddImageMosaic | Available free of charge for a limited period of time | 0.0074 | 1,000 calls | |
ImageCropping | Image cropping suggestions | DetectImageCropping | image/crop,g_auto | 0.1415094 | 0.1415094 | 1,000 calls |
ImageQRCodes | Quick response (QR) code recognition | DetectImageCodes | image/codes | 0.1132075 | 0.1132075 | 1,000 calls |
ImageSplicing | Image concatenation | CreateImageSplicingTask | Available free of charge for a limited period of time |
| Thousand times | |
ImageToPDF | Image-to-PDF conversion | CreateImageToPDFTask | Available free of charge for a limited period of time | 0.0074 | 1,000 images | |
ImageScoring | Image quality assessment | DetectImageScore | image/scoring | 0.0424528 | 0.0424528 | 1,000 calls |
LocationDateClustering | Time-space clustering | CreateLocationDateClusteringTask | Available free of charge for a limited period of time | Available free of charge for a limited period of time | 1,000 calls | |
SimilarImageClustering | Image clustering | CreateSimilarImageClusteringTask | Available free of charge for a limited period of time | Available free of charge for a limited period of time | 1,000 calls | |
Blindwatermark | Blind watermarking |
|
| 0.0990566 | 0.0990566 | 1,000 calls |
ReverseGeocoding | Reverse geocoding | DetectMediaMeta Note You are charged when geographic location information is present in the media file. | 0.1415094 | 0.1415094 | 1,000 calls | |
ImageTexts | Optical character recognition (OCR) | DetectImageTexts | 7.0754717 | 7.0754717 | 1,000 calls |
Metadata management
The following table describes billable items in the metadata management category.
Billable item | Description | Related API operations | Related x-oss-process operations | Price before 11:00 on July 28, 2025 (USD) | Price after 11:00 on July 28, 2025 (USD) | Unit |
StandardQueryL0 | Basic query |
| task/get | 0.014 | 0.00074 | 1,000 calls |
StandardQueryL1 | Standard query |
| 0.0283 | 0.0015 | 1,000 calls | |
StandardQueryL2 | Advanced queries |
| 0.708 | 0.074 | Thousand times | |
MediaMeta | Media information collection |
|
| 0.1415094 | 0.1415094 | 1,000 calls |
SemanticAnalyze | Semantic analysis | SemanticQuery | Available free of charge for a limited period of time | 0.52 | 1,000 calls |
Media processing
The following table describes billable items in the media processing category.
Billable item | Description | Related API operations | Related x-oss-process operations | Price before 11:00 on July 28, 2025 (USD) | Price after 11:00 on July 28, 2025 (USD) | Unit |
AudioCompress | Audio transcoding | CreateMediaConvertTask |
| 0.0000141509 | 0.0000141509 | Second (audio length) |
VideoCompressCopy | Container format conversion | CreateMediaConvertTask | 0.0001415094 | 0.0001415094 | Second (video length) | |
VideoCompress264LD | H.264 transcoding-LDNote* | CreateMediaConvertTask |
| 0.0000509434 | 0.0000509434 | Second (video length) |
VideoCompress264SD | H.264 transcoding-SDNote* | CreateMediaConvertTask |
| 0.0000707547 | 0.0000707547 | Second (video length) |
VideoCompress264HD | H.264 transcoding-HDNote* | CreateMediaConvertTask |
| 0.0001273585 | 0.0001273585 | Second (video length) |
VideoCompress2642K | H.264 transcoding-2KNote* | CreateMediaConvertTask |
| 0.0002830189 | 0.0002830189 | Second (video length) |
VideoCompress2644K | H.264 transcoding-4KNote* | CreateMediaConvertTask |
| 0.0006367925 | 0.0006367925 | Second (video length) |
VideoCompress265LD | H.265 transcoding-LDNote* | CreateMediaConvertTask |
| 0.0002122642 | 0.0002122642 | Video frames per second |
VideoCompress265SD | H.265 transcoding-SDNote* | CreateMediaConvertTask |
| 0.0003537736 | 0.0003537736 | Video frames per second |
VideoCompress265HD | H.265 transcoding-HDNote* | CreateMediaConvertTask |
| 0.0007075472 | 0.0007075472 | Second (video length) |
VideoCompress2652K | H.265 transcoding-2KNote* | CreateMediaConvertTask |
| 0.0011320755 | 0.0011320755 | Second (video length) |
VideoCompress2654K | H.265 transcoding-4KNote* | CreateMediaConvertTask |
| 0.0022641509 | 0.0022641509 | Second (video length) |
MediaAnimation | Video-to-animated-image conversion | CreateMediaConvertTask | video/animation | Available free of charge for a limited period of time |
| 1,000 frames |
ExtractSubtitleText | Video text caption extraction | CreateMediaConvertTask | Available free of charge for a limited period of time | 0.223 | 1,000 ingest endpoints | |
ExtractSubtitleImage | Video image caption extraction | CreateMediaConvertTask | Available free of charge for a limited period of time | 0.015 | 1,000 frames | |
VideoFraming | Video frame capture | CreateMediaConvertTask |
| 0.142 | 0.015 | 1,000 frames |
VideoClassification | Video label detection | CreateVideoLabelClassificationTask | 7.0754717 | 7.0754717 | 1,000 calls | |
LiveTranscoding | Live transcodingNote* | GenerateVideoPlaylist |
| 0.0000141509 | 0.0000141509 | CountUnit |
Document processing
The following table describes billable items in the document processing category.
For a document in a project created before December 1, 2023, you are charged for this billable item based on the number of times the document is opened. For a document in a project created on December 1, 2023 or later, you are charged for this billable item based on the number of API operation calls.
Billable item | Billing Item Description | Related API operations | Related x-oss-process operations | Price before 11:00 on July 28, 2025 (USD) | Price after 11:00 on July 28, 2025 (USD) | Unit |
DocumentConvert | Document conversion | CreateOfficeConversionTask |
| 11.3207547 | 11.3207547 | 1,000 calls |
Document text extraction | ExtractDocumentText | |||||
DocumentWebofficeEdit | Document editing (WebOffice)Note* |
| doc/edit | 2.8301887 | 2.8301887 | 1,000 calls |
DocumentWebofficePreview | Document preview (WebOffice)Note* |
| doc/preview | 1.4150943 | 1.4150943 | 1,000 calls |
DocumentWebofficeCachePreview | Cache preview (WebOffice) |
| 0.9905660 | 0.9905660 | 1,000 calls Important You are charged based on the number of API operation calls. |
File processing
The following table describes billable items in the file processing category.
Billable item | Description | Related API operations | Related x-oss-process operations | Price before 11:00 on July 28, 2025 (USD) | Price after 11:00 on July 28, 2025 (USD) | Unit |
PointCloudCompress | Point cloud compression | CreateCompressPointCloudTask | pointcloud/compress | Available free of charge for a limited period of time | 0.03 | One thousand times |
FileProcess | File package download | CreateFileCompressionTask | Available free of charge for a limited period of time | 0.00074 | GB | |
Archive file decompression | CreateFileUncompressionTask | Available free of charge for a limited period of time | ||||
FilePreview | Archive file preview | CreateArchiveFileInspectionTask | Available free of charge for a limited period of time | 0.0074 | TB |
API operations with multiple billable items
The SemanticQuery operation generates StandardQueryL2 and SemanticAnalyze fees.
The CompareImageFaces operation doubles the ImageFace fee.
The SearchImageFigureCluster operation generates ImageFace and FaceSearch fees.
The CreateFacesSearchingTask operation generates ImageFace and FaceSearch fees.
Video transcoding description
H.264 transcoding: Output videos use the H.264 codec.
H.265 transcoding: Output videos use the H.265 codec.
LD: The resolution of output videos is less than or equal to 640 × 480 pixels.
SD: The resolution of output videos is less than or equal to 1,280 × 720 pixels.
HD: The resolution of output videos is less than or equal to 1,920 × 1,080 pixels.
2K: The resolution of output videos is less than or equal to 2,560 × 1,440 pixels.
4K: The resolution of output videos is less than or equal to 3,840 × 2,160 pixels.
Document preview and editing billing description
For a project created before December 1, 2023, you are charged for previewing and editing a document based on the number of times the document is opened, not the number of API operation calls.
For a project created on December 1, 2023 or later, you are charged based on the number of API operation calls. If you want to switch to the new billing model, create a new project.
In API call-based billing, one API call allows only one user to use the feature. If multiple users use the information returned by the API call, only the last user has access to the document and the access permissions of other users are revoked.
If you set the Permission.Readonly parameter to true in the GenerateWebofficeToken operation, you are charged for online document previewing. If you set the Permission.Readonly parameter to false, you are charged for online document editing.
Billing for calls to the RefreshWebofficeToken operation varies based on the value of the Permission.Readonly parameter in the GenerateWebofficeToken operation. If you set the Permission.Readonly parameter to true, you are charged a document preview fee for calling the RefreshWebofficeToken operation. If you set the parameter to false, you are charged a document editing fee for calling the RefreshWebofficeToken operation.
Live transcoding billing description
Fee composition:
When generating a playlist, you can control the duration of initial transcoding through the InitialTranscode parameter setting, which will incur LiveTranscoding fees.
When playing videos, if you play ts files that have not been transcoded before, it will trigger new transcoding, which will incur LiveTranscoding fees.
The fees charged by Object Storage Service (OSS): You are charged by OSS for using IMM to read videos from OSS for transcoding, write transcoded videos to OSS, and read videos from OSS for video playback. For more information about OSS fees, see OSS billable items.
Metering rules for LiveTranscoding billing:
Video
The efficiency (referred to as eff in the following formula) is 0.3 for H.264 output videos and 1.8 for H.265 output videos.
Metering is based on the following formula:
Ceiling (eff * Ceiling(Height/240) * Ceiling(Width/240) * Ceiling(FrameRate/30) + 1 ) * Ceiling(VideoStreamDuration)Audio
The efficiency (referred to as eff in the following formula) is 0.3.
Metering is based on the following formula:
Ceiling(eff * Ceiling(AudioStreamDuration))
Billing rules: You are charged separately for each processed video stream or audio stream. Video streams are specified by TargetVideo.Stream and audio streams are specified by TargetAudio.Stream. The following content provides billing examples for LiveTranscoding:
Example 1: No fee for the LiveTranscoding billable item is generated if no video in a generated playlist is played.
For example, you call the GenerateVideoPlaylist operation with InitialTranscode set to 0 and TranscodeAhead left empty to create a video playlist for a 38-minute H.264 output video at a resolution of 800 × 600 pixels and a frame rate of 30 fps. No video in the playlist is played.
Example 2: A fee for the LiveTrancoding billable item for initial transcoding is generated if a generated playlist has an initial transcoding configuration and no video in the playlist is played.
For example, you call the GenerateVideoPlaylist operation with InitialTranscode set to 30 and TranscodeAhead left empty to create a video playlist for a 38-minute H.264 output video at a resolution of 800 × 600 pixels and a frame rate of 30 fps. No video in the playlist is played.
The fee for the following billable item is generated:
LiveTranscoding (CU count calculation formula):
Ceiling((0.3 * Ceiling(800/240) * Ceiling(600/240) * Ceiling(30/30) + 1 ) * (Ceiling(30)) + Ceiling(0.3 * Ceiling(30)) = 159 (CountUnit)
Example 3: A fee for the LiveTranscoding billable item is generated for the played segments of video content in a generated playlist.
For example, you call the GenerateVideoPlaylist operation with InitialTranscode set to 0 and TranscodeAhead left empty to create a video playlist for a 38-minute H.264 output video at a resolution of 800 × 600 pixels and a frame rate of 30 fps. Then, you play the video from the beginning to the 5th minute (transcoded to 2 minutes ahead by default) and skip to the 15th minute, from which the playback continues to the end.
The fee for the following billable item is generated:
LiveTranscoding (CU count calculation formula):
Ceiling((0.3 * Ceiling(800/240) * Ceiling(600/240) * Ceiling(30/30) + 1) * (Ceiling((5+2)*60) + Ceiling((38-15)*60)) + Ceiling(0.3 * Ceiling((5+2) * 60)) + Ceiling(0.3 * Ceiling((38-15) * 60) = 9540 (CountUnit)
Example 4: A fee for the LiveTranscoding billable item is generated only once if the video is played by multiple users.
For example, you call the GenerateVideoPlaylist operation with InitialTranscode set to 0 and TranscodeAhead left empty to create a video playlist for a 38-minute H.264 output video at a resolution of 800 × 600 pixels and a frame rate of 30 fps.
User A uses the playlist to play the video from the beginning to the 5th minute and exits the playback.
User B uses the playlist to play the video from the 15th minute to the end.
User C uses the playlist to play the video from the beginning to the end.
The fees for the following billable items are generated:
LiveTranscoding (CU count calculation formula):
Ceiling((0.3 * Ceiling(800/240) * Ceiling(600/240) * Ceiling(30/30) + 1) * Ceiling(38*60) + Celling(0.3 * Celling(38 * 60)) = 12084 (CountUnit)
Terms:
Width: the width of the output video
Height: Width of the output video resolution
FrameRate: the frame rate
VideoStreamDuration: the length of the video stream
AudioStreamDuration: the length of the audio stream
eff: the efficiency used to calculate the metered amount
Ceiling(x): a function that returns the smallest nearest integer greater than or equal to the specified number
Operators and billable items
When you create metadata indexes by binding an OSS bucket or calling the IndexFileMeta or BatchIndexFileMeta operation, the operators described in Mappings between workflow templates and operators generate data processing fees, index storage fees, and OSS request fees. OSS request fees are charged by OSS. For more information, see OSS request fees. The following table provides the mappings between operators and billable items:
Operator | Billable item | Charged by |
OSSMeta operator | OSS | |
MIME operator | Free of charge | None |
FaceDetection operator | ImageFaceNote* | IMM |
LabelClassification operator (for images) | ImageClassificationNote* | IMM |
LabelClassification operator (for videos) | VideoClassification | IMM |
ImageScoring operator | ImageScoringNote* | IMM |
ReGEO operator | ReverseGeocoding | IMM |
MediaMeta operator | MediaMeta | IMM |
EXIF operator | OSS | |
ExtractDocumentText operator | DocumentConvert | IMM |
ExtractImageEmbeddings operator | Available free of charge for a limited period of time | IMM |
To process images in various formats, IMM uses the image processing capabilities of Object Storage Service (OSS) to perform one or more format conversions, image scaling, or other operations on images. These operations generate corresponding fees, which are charged by OSS. For more information about these fees, see Data processing fees.
External request fees
When you use Intelligent Media Management (IMM) to access OSS, you are charged OSS operation calling fees by OSS. For more information, see Request fees.