Model Serving & Economics
Inference endpoint
A network address where applications can send requests to a deployed model.
Example
An application sends prompts to a stable HTTPS endpoint backed by a deployed model.
Why it matters
It gives an application a consistent place to reach the AI service.
You'll hear it
“Which address should our app send these requests to?”
Can you control it?
Set by the team
The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.
Common questions
- Can I use it by opening it in a browser?
- Usually an application must send a properly formatted request; it may not work like a normal webpage.
- Can one endpoint handle many people at once?
- Yes, within the service's limits. Busy periods may still cause waiting or rejected requests.
- Can the model change while the address stays the same?
- Yes. Check the provider's version settings if your application needs consistent behavior over time.