Model provider
Choose, for the whole organization, who processes your model requests.
Both options run the same product features; the difference is who processes your organization's AI requests and what happens to them afterward. It's the decision your compliance or IT policy may care about, so it belongs to admins: open the user menu and choose Inference provider. The choice applies to every member and every deal.
The choice
| Provider | What it means for your data |
|---|---|
| Amazon Bedrock | Requests are processed within AWS infrastructure. |
| Claude Platform on AWS | Requests are processed by Anthropic outside the AWS boundary and retained for up to 30 days. |
The way to think about it: if your firm's policy requires deal data to stay within AWS, choose Amazon Bedrock. If that constraint doesn't apply to you, either option works, and the difference you're accepting with Claude Platform is that Anthropic processes the requests and keeps them for up to 30 days.
When the change takes effect
The choice applies to newly opened sessions only. Sessions already open keep the provider they started with; open a new session to pick up the change.
Learn more
- Sessions: how to open a new session so the change applies.