Microsoft logo

Swin S3 Base


Swin S3 Base is Microsoft's image to text model. A base-scale Swin Transformer trained with the S3 (Self-Supervised Swin) approach at 224px resolution for image classification.
Specifications
Canonical IDmicrosoft-swin-s3-base
TypeImage to Text
StatusActive
CreatorMicrosoftMicrosoft
Input ModalitiesImage
Output ModalitiesText

Capabilities

Input1/5
Text·
Image
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Swin S3 BaseCurrent
Swin Base 4 12 384Available
Swin LargeAvailable
Swin S3 SmallAvailable
Swin S3 TinyAvailable
Swin SmallAvailable
Swin TinyAvailable

Model IDs