Managing Routing Profiles
Routing profiles define how OCI Generative AI routes on-demand model requests across user-selected OCI regions.
A routing profile specifies one supported on-demand model and one or more target OCI regions within the same realm where that model is available. When you reference the routing profile in a supported inference request, Generative AI routes the request only among the target regions in the profile.
Use routing profiles to access a selected model across an approved regional scope without building application-side cross-region routing. For the regional availability of each model, see Generative AI Models by Region.
Use a routing profile to access an on-demand model hosted in another region. The Chat API, OpenAI-compatible Chat Completions API, and Responses API are supported when the selected model supports the API. For regions without local on-demand model hosting, including UAE Central (Abu Dhabi), which also hosts dedicated models, see Regions without local on-demand model hosting.
Routing profiles are also available in regions where OCI Generative AI hosts models. For example, if an on-demand model is available in US Midwest (Chicago) but not US East (Ashburn), create a routing profile in Ashburn and select Chicago as its target region. Select the profile in Ashburn's Playground or reference it in a request to the Ashburn API endpoint. Inference through routing profiles uses on-demand mode.
You can perform the following tasks to create and manage routing profiles: