The first 1000 images/mo are free which you can see on Google's pricing page cloud.google.com/vision/pricing. I think the vision API is designed for images but you can submit stills from your videos. The GCP platform is fairly scalable can handle high volumes of requests. For a social media use case like this one you'd want to do filtering server side to prevent cases where people try to bypass on-device filtering.
For further actions, you may consider blocking this person and/or reporting abuse
We're a place where coders share, stay up-to-date and grow their careers.
Are the APIs free? what is the cost/image? how many image/sec at what latency? can it support real time video?
Is it better (energy, latency, throughput) to do the classification on the device using or use cloud APIs
Thanks.
The first 1000 images/mo are free which you can see on Google's pricing page cloud.google.com/vision/pricing. I think the vision API is designed for images but you can submit stills from your videos. The GCP platform is fairly scalable can handle high volumes of requests. For a social media use case like this one you'd want to do filtering server side to prevent cases where people try to bypass on-device filtering.