Skip to content

Document that min replicas for hosted agents can be 0 to incur less charges #634

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
gukoff wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Document that min replicas for hosted agents can be 0 to incur less charges #634

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions articles/ai-foundry/default/agents/concepts/hosted-agents.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -425,6 +425,17 @@ Here's an example:
az cognitiveservices agent start --account-name myAccount --project-name myProject --name myAgent --agent-version 1
```

> [!TIP]
> - To minimize charges when idle, set `--min-replicas 0`. The service scales to zero and doesn't allocate compute when not serving requests.
> - The first request after scaling to zero incurs a cold start. To avoid cold starts, keep at least one warm replica by setting `--min-replicas 1` (or higher), trading steady-state cost for lower latency.
> - You can adjust replica settings later with a non-versioned update: `az cognitiveservices agent update --min-replicas <n> --max-replicas <m>`.
>
> Example (scale-to-zero when idle):
>
> ```bash
> az cognitiveservices agent start --account-name myAccount --project-name myProject --name myAgent --agent-version 1 --min-replicas 0 --max-replicas 2
> ```

When you start an agent:

- Current status: **Stopped**
Expand Down