Next, you can now control where inference runs for Claude Managed Agents.
- Source
- x.com
- Date
Next, you can now control where inference runs for Claude Managed Agents. Set model.inference_geo to US or global. Pinning to `global` runs wherever there's capacity at the standard rate and `us` keeps it in-region and bills at 1.1x.
Context
Anthropic added a choice about where Claude Managed Agents performs , the computation that generates model responses. Its August 7 announcement offers US-only processing at 1.1 times the standard rate, or global processing wherever capacity is available at the standard rate. Developers select this through model.inference_. This gives teams a specific location-versus-price choice for model computation; the announcement's scope does not establish where every file, log or external tool operation resides. The post and configuration example describe the setting.
- inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
- generative engine optimization — Making a site the source an AI assistant cites when answering, rather than a link in a list of ten blue results.
Checking sign-in…
Loading comments…