Skip to content
Terms.

Data residency changed Anthropic, Jun 9, 2026

Anthropic · Jun 9, 2026 · 11 added, 10 removed · found in an Internet Archive capture

Archived copyAll Anthropic terms
  1. Added: Inference geo: Controls where model inference runs, on a per-request basis. Set through the inference_geo API parameter or as a workspace default.
  2. Added: Workspace geo: Controls where data is stored at rest and where endpoint processing (such as image transcoding and code execution) happens. Configured at the workspace level in the Claude Console .
  3. Added: Claude Managed Agents does not support the inference_geo parameter, but respects the Workspace geo configured in Console. With self-hosted sandboxes , tool execution and the sandbox filesystem stay on infrastructure you control.
  4. Removed: Inference geo: Controls where model inference runs, on a per-request basis. Set via the inference_geo API parameter or as a workspace default.
  5. Removed: Workspace geo: Controls where data is stored at rest and where endpoint processing (image transcoding, code execution, etc.) happens. Configured at the workspace level in the Console .
  6. Removed: Claude Managed Agents does not support the inference_geo parameter, but respects the Workspace geo configured in Console.
  7. Added: The inference_geo parameter is supported on Claude Opus 4.6, Claude Sonnet 4.6, and later models. Requests with inference_geo on Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, or earlier models return a 400 error.
  8. Added: The inference_geo parameter is available on the Claude API (first-party) and Claude Platform on AWS . On Amazon Bedrock, Vertex AI, and Microsoft Foundry, the inference region is determined by the endpoint URL or inference profile, so inference_geo is not applicable. The inference_geo parameter is also not available through the OpenAI SDK compatibility endpoint .
  9. Removed: The inference_geo parameter is supported on Claude Opus 4.6 and all subsequent models. Older models released before Opus 4.6 do not support the parameter. Requests with inference_geo on legacy models return a 400 error.
  10. Removed: The inference_geo parameter is only available on the Claude API (1P). On third-party platforms (AWS Bedrock, Google Vertex AI), the inference region is determined by the endpoint URL or inference profile, so inference_geo is not applicable. The inference_geo parameter is also not available via the OpenAI SDK compatibility endpoint .
  11. Added: Claude Platform on AWS: Workspace geo is not configurable. Workspaces are provisioned through the AWS Console, and the Claude Console Workspaces page is read-only. Claude Managed Agents sessions on this platform run with an effective Workspace geo of "us" , which is currently the only available workspace geo. See Claude Platform on AWS for data residency considerations specific to that platform.
  12. Added: Claude Opus 4.6, Claude Sonnet 4.6, and later: US-only inference ( inference_geo: "us" ) is priced at 1.1x the standard rate across all token pricing categories (input tokens, output tokens, cache writes, and cache reads).
  13. Added: Global routing ( inference_geo: "global" ): Standard pricing applies.
  14. Added: Older models: Don't support inference_geo (see Model availability ); standard pricing applies. Requests that include the parameter return a 400 error.
  15. Added: This pricing applies to the Claude API (first-party) and Claude Platform on AWS. Partner-operated platforms (Bedrock and Vertex AI) have their own regional pricing. See Data residency pricing for details.
  16. Removed: Claude Opus 4.6 and newer: US-only inference ( inference_geo: "us" ) is priced at 1.1x the standard rate across all token pricing categories (input tokens, output tokens, cache writes, and cache reads).
  17. Removed: Global routing ( inference_geo: "global" or omitted): Standard pricing applies.
  18. Removed: Older models: Existing pricing is unchanged regardless of inference_geo settings.
  19. Removed: This pricing applies to the Claude API (1P) only. Third-party platforms (AWS Bedrock, Google Vertex AI) have their own regional pricing. See the pricing page for details.
  20. Added: Inference geo: Only "us" and "global" are available.
  21. Removed: Inference geo: Only "us" and "global" are available at launch. Additional regions will be added over time.
About this change
Page
platform.claude.com/docs/en/manage-claude/data-residency
Kind
Documentation
Text hash
f07467d4d2d1 to 897b0e0fd235
Dated by
the first Internet Archive capture sampled that shows the new text; the change happened on or before this date

Terms changes by email

Mondays, only in weeks when a watched page changed.

Double opt-in. Unsubscribe any time.