SSD ResNet 50 V1 FPN is Google's image to text model. An SSD object detection model with a ResNet-50 V1 FPN backbone balancing accuracy and efficiency on the COCO benchmark.
google-ssd-resnet50-1 |
| Image to Text |
| Active |
| 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 |
|---|---|---|---|---|---|
| SSD MobileNet FPNLite 2 | — | — | — | — | Available |
| SSD Mobilenet V2 | — | — | — | — | Available |
| SSD ResNet 50 V1 FPN | — | — | — | — | Current |
| SSD MobileNet V1 FPN | — | — | — | — | Available |
| SSD Mobilenet V1 FPN 640x640 | — | — | — | — | Available |
| SSD ResNet 101 V1 FPN | — | — | — | — | Available |
| SSD ResNet 152 V1 FPN | — | — | — | — | Available |
| SSD | — | — | — | — | Available |