Inference
Self-hosting
Running an open-weight model on your own servers or cloud instances instead of calling a provider's API.
Self-hosting keeps data in-house and can be cheaper at high, steady volume, but you take on hardware, scaling and maintenance. For small or spiky usage, APIs are usually cheaper.
Frequently asked questions
What does Self-hosting mean?
Running an open-weight model on your own servers or cloud instances instead of calling a provider's API. Self-hosting keeps data in-house and can be cheaper at high, steady volume, but you take on hardware, scaling and maintenance. For small or spiky usage, APIs are usually cheaper.