Swin Base 4 12 384
Swin Base 4 12 384 is Microsoft's image to text model. A Swin Transformer-based image classification model using shifted window attention, configured for high-resolution 384×384 input with a base-scale architecture.
microsoft-swin |
| Image to Text |
| Active |
| Microsoft |
| Image |
| Text |
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
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Swin Base 4 12 384 | — | — | — | — | Current |
| Swin Large | — | — | — | — | Available |
| Swin S3 Base | — | — | — | — | Available |
| Swin S3 Small | — | — | — | — | Available |
| Swin S3 Tiny | — | — | — | — | Available |
| Swin Small | — | — | — | — | Available |
| Swin Tiny | — | — | — | — | Available |