Features - Claude.ai Documentation

Claude Desktop on third-party (3P) is a deployment mode of Claude Desktop that routes all model inference through a provider you configure. Pricing is token-based consumption billed by your cloud provider, with no seat licensing.

Key differences from Claude Enterprise

The Claude Enterprise features in this table are enduring differences between Claude Enterprise and Claude Desktop on 3P. Anthropic doesn’t have the technical ability to bring these features to Claude Desktop on 3P based on its local and third-party architecture.

Feature	Claude Enterprise	Claude Desktop on 3P
Connect to your cloud provider for inference	No	Yes
Data residency in multiple regions	No	Yes
Conversation history stored on device	No	Yes
Mobile and claude.ai web-based access	Yes	No
Sessions in Anthropic’s cloud	Yes	No
Sharing between users	Yes	No
Voice mode	Yes	No
Claude Security and Claude Tag	Yes	No

Features in Claude Desktop on 3P

Some features have limits or need setup, described in Good to know about Claude Desktop on 3P. Claude Desktop on 3P is administered from the web-based admin console, and can also be configured through MDM or a bootstrap server.

Everyday work

Web and browser

Connectors and extensions

Code

Administration

Monitoring and retention

Good to know about Claude Desktop on 3P

Notes on setup, limits, monitoring, and data handling

Topic	What to know
Sessions and scheduled tasks	Sessions are local, except Code sessions over SSH, and the device must be awake to run long processes and scheduled tasks.
Memory	Memory in Claude Desktop on 3P is stored on the device, not on Anthropic infrastructure. Chat-history search and nightly summary generation are not available in Chat on 3P.
Web search	Amazon Bedrock deployments and gateways that do not forward Anthropic server tools need a web search provider configured first.
Claude in Chrome	Claude in Chrome works with Claude Desktop on 3P only in organizations managed from the Enterprise Admin Console.
Automatically approve in Cowork	Cowork offers the Automatically approve mode when an administrator sets `autoModeEnabled` to `true`.
User management via UI and RBAC	With the Enterprise Admin Console, administrators add users and groups, connect single sign-on and SCIM, assign administrator roles, and set per-group permission policies from Organization settings on claude.ai. Deployments configured through MDM or a bootstrap server manage access through those channels.
Monitoring	Many capabilities of the Compliance API and Analytics API can be achieved via OpenTelemetry export to your own collector.
Telemetry	Claude Desktop on 3P sends crash reports and product analytics to Anthropic by default. This telemetry contains no prompt or response content, and you can fully disable it via managed configuration.
Data handling	Data handling at the inference endpoint depends on the provider you configure. For Google Cloud’s Agent Platform and Amazon Bedrock, data handling is governed by Google Cloud and Amazon Bedrock respectively. For Microsoft Foundry, Anthropic operates the Claude models and handles conversation data as an independent processor for Microsoft. For the Anthropic API, Anthropic processes conversation data under your Anthropic agreement, as described on the Claude API page.