Use case
Use cases
Workload patterns for private, region-pinned inference. Each page states the problem, the architecture, the verified model options and the governance notes.
- Private document search pipelines
Run your own document search and retrieval pipeline on region-pinned inference, so the content and the compute stay in the region you choose.
- AI coding & source-code assistance
Point coding assistants at region-pinned inference so source code never has to leave the region and provider control you set.
- Document analysis & extraction
Analyze long documents — contracts, reports, records — in a single pass on a 320K-context model, in the region the document belongs to.
- Classification & summarization
High-volume classification and summarization jobs on region-pinned inference, with fair-use plan limits per API key.
- Internal enterprise assistants
Internal assistants for your people on top of region-pinned inference: the questions and answers stay under your governance, in your region.
- Governed AI agents
Agent loops that call model capabilities through one governed, region-pinned endpoint — the orchestration stays yours, the inference stays pinned.