You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-foundry/model-inference/faq.yml
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -33,7 +33,7 @@ sections:
33
33
- *Resource involved*: standard deployments are deployed within an AI project resource, while Foundry Models is part of the Azure AI Foundry resource.
34
34
- *Deployment options*: standard deployments allow regional deployments, while Foundry Models allows deployments under a global capacity.
35
35
- *Models*: Foundry Models also supports deploying Azure OpenAI models.
36
-
- *Endpoint*: standard deployments creates one endpoint and credential per deployment, while Foundry Models creates one endpoint and credential per resource.
36
+
- *Endpoint*: standard deployments create one endpoint and credential per deployment, while Foundry Models creates one endpoint and credential per resource.
37
37
- *Model router*: Foundry Models allows you to switch between models without changing your code using a model router.
0 commit comments