api-20260826T150709Z / documentation capture

agents-and-tools/tool-use/browser-use-tool Changed · +3 / -3 lines

from line 7

77## Compatibility

88- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): eligible (excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements))

99- Supported models: `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-sonnet-5`, `claude-opus-4-8`

10- Platforms: Claude API; not available on Claude Platform on AWS, Amazon Bedrock, Google Cloud, Microsoft Foundry

10- Platforms: Claude API, Google Cloud; not available on Claude Platform on AWS, Amazon Bedrock, Microsoft Foundry

1111

1212The browser use tool lets Claude navigate, read, and interact with webpages in a browser that your application runs. It works with the page both through its structure (the accessibility tree, elements, forms, and tabs) and through pixels (screenshots and viewport coordinates), whereas the [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) works with a whole desktop through screenshots and coordinates alone. It's an Anthropic-defined [client toolset](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference#client-toolsets): one `browser_toolset_20260801` entry in your `tools` array gives Claude 27 member tools by default, such as `navigate`, `read_page`, `left_click`, and `screenshot`, plus four more (`javascript_exec`, `file_upload`, `read_console`, and `read_network`) when you [enable them](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#enable-optional-member-tools). Your application runs every call against its own browser automation; nothing runs on Anthropic's side. It isn't currently available in [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/tools). This page says "your application" for the agent loop that calls the Messages API and "your executor" for the part of it that drives the browser and produces tool results.

1313

from line 17

1717

1818## Quick start

1919

20The browser use tool is available on the Claude API with no beta header: add one entry of type `browser_toolset_20260801`, with no `name`, to the `tools` array of a [Messages API](https://platform.claude.com/docs/en/api/messages/create) request.

20The browser use tool is available on the Claude API and [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai): add one entry of type `browser_toolset_20260801`, with no `name`, to the `tools` array of a [Messages API](https://platform.claude.com/docs/en/api/messages/create) request.

2121

2222<CodeGroup>

2323 ```bash cURL

from line 1529

15291529

15301530## Limitations

15311531

1532* **Platform availability:** Browser use is available on the Claude API only.

1532* **Platform availability:** Browser use is available on the Claude API and [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai).

15331533* **Whole-input streaming only:** When you stream, each member's `input` arrives as one complete `input_json_delta` ([Client toolsets](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference#client-toolsets)).

15341534* **Element references are best-effort:** Highly dynamic pages (virtualized lists, canvas-rendered interfaces, pages that re-render on scroll) might not expose stable references, and Claude falls back to screenshots and coordinate clicks there.

15351535* **`read_console` and `read_network` depend on your browser automation:** They report only what it can capture, and only from the moment it attached to a tab.

agents-and-tools/tool-use/computer-use-tool Changed · +3 / -3 lines

from line 7

77## Compatibility

88- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): eligible (excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements))

99- Supported models: `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-sonnet-5`, `claude-opus-4-8`

10- Platforms: Claude API, Claude Platform on AWS (beta), Amazon Bedrock (beta), Google Cloud (beta), Microsoft Foundry (beta)

10- Platforms: Claude API, Claude Platform on AWS (beta), Amazon Bedrock (beta), Google Cloud, Microsoft Foundry (beta)

1111- Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, and Claude Opus 4.5 support computer use only through the earlier `computer_20251124` tool version, which requires a beta header; see [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions).

12- Platforms other than the Claude API currently offer only the [earlier beta tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions).

12- Platforms other than the Claude API and Google Cloud currently offer only the [earlier beta tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions).

1313

1414Claude can interact with computer environments through the computer use tool, which provides screenshot capabilities and mouse/keyboard control for autonomous desktop interaction.

1515

from line 18

1818For tasks that stay inside webpages, the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) is the closer fit: its member tools read and act on the page itself, and it doesn't need a full desktop environment.

1919

2020<Note>

21 Computer use is available on the Claude API as the `computer_toolset_20260801` toolset, with no beta header; see [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) for the supported models.

21 Computer use is available on the Claude API and [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) as the `computer_toolset_20260801` toolset; see [Compatibility](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#compatibility) for the supported models.

2222

2323 Existing `computer_20251124` integrations keep working, and earlier tool versions remain available in beta for models and platforms that don't support the toolset. See [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124) to upgrade, or [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions) for the beta headers.

2424</Note>

build-with-claude/claude-platform-on-aws Changed · +3 / -3 lines

## Claude Platform on AWS versus Amazon Bedrock ## Claude Platform on AWS vs Amazon Bedrock

from line 14

1414

1515Claude models run on Anthropic-managed infrastructure. This is a commercial integration for billing and access through AWS. Anthropic is the data processor for inference inputs and outputs. AWS processes billing and identity metadata under the marketplace model. Customers using Claude through Claude Platform on AWS are subject to Anthropic's [data use terms](https://www.anthropic.com/legal).

1616

17Claude Platform on AWS has the following operational characteristics: data may not reside in AWS, inference may route to Anthropic's primary cloud, and subservices may change without notice. Set the [`inference_geo`](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#data-residency) parameter per request to pin inference to a specific geography.

17Claude Platform on AWS has the following operational characteristics: data might not reside in AWS, inference might route to Anthropic's primary cloud, and subservices might change without notice. Set the [`inference_geo`](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#data-residency) parameter per request to pin inference to a specific geography.

1818

1919Claude Platform on AWS follows the same data retention policy as the first-party Claude API. Zero Data Retention (ZDR) is available on request. Contact your Anthropic account representative to enable it for your organization.

2020

21## Claude Platform on AWS vs Amazon Bedrock

21## Claude Platform on AWS versus Amazon Bedrock

2222

2323Both offerings let you use Claude through AWS, but they differ in architecture, API surface, and feature availability.

2424

from line 542

542542* **Batch processing:** Submit batch requests for high-throughput workloads.

543543* **Prompt caching:** Cache tools, system prompts, and message history to reduce latency and cost. All prompt caching capabilities (5-minute TTL, 1-hour TTL, and automatic caching) are available.

544544* **Files API:** Upload and reference files across requests.

545* **Customer-managed encryption keys (CMEK):** [CMEK](https://platform.claude.com/docs/en/manage-claude/cmek) is available with [AWS KMS](https://platform.claude.com/docs/en/manage-claude/cmek-aws-kms) keys only. Google Cloud KMS and Azure Key Vault keys cannot be registered. Create, validate, and attach keys in the [Claude Console](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#using-the-claude-console). The `external_keys` Admin API endpoints are not currently available. The key must be in the same AWS region as the workspace it is attached to.

545* **Customer-managed encryption keys (CMEK):** [CMEK](https://platform.claude.com/docs/en/manage-claude/cmek) is available with [AWS KMS](https://platform.claude.com/docs/en/manage-claude/cmek-aws-kms) keys only. Google Cloud KMS and Azure Key Vault keys cannot be registered. Create and attach keys in the [Claude Console](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#using-the-claude-console). There is no separate validation step; the key policy is first exercised when a workspace starts using the key, so a key policy problem surfaces at that point rather than at registration. The `external_keys` Admin API endpoints are not currently available. The key must be in the same AWS region as the workspace it is attached to.

546546* **Compliance API:** The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) is available. Access is authorized through the AWS IAM [`ListComplianceActivities` action](https://platform.claude.com/docs/en/api/claude-platform-on-aws-iam-actions#compliance).

547547

548548See the [comparison table](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#claude-platform-on-aws-vs-amazon-bedrock) for feature-availability differences from Amazon Bedrock.

build-with-claude/overview Changed · +7 / -7 lines

from line 68

6868

6969### Client-side tools

7070

72| ----------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------ | --------------------------------------------------------------------------------------------- |

73| [Bash](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool) | Execute bash commands and scripts to interact with the system shell and perform command-line operations. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

74| [Browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) | Navigate, read, and interact with webpages in your own browser environment. | ZDR eligible | <PlatformAvailability claudeApi /> |

75| [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) | Control computer interfaces by taking screenshots and issuing mouse and keyboard commands. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAwsBeta bedrockBeta vertexAiBeta azureAiBeta /> |

76| [Memory](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool) | Enable Claude to store and retrieve information across conversations. Build knowledge bases over time, maintain project context, and learn from past interactions. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

77| [Text editor](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool) | Create and edit text files with a built-in text editor interface for file manipulation tasks. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

72| ----------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------ | ----------------------------------------------------------------------------------------- |

73| [Bash](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool) | Execute bash commands and scripts to interact with the system shell and perform command-line operations. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

74| [Browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) | Navigate, read, and interact with webpages in your own browser environment. | ZDR eligible | <PlatformAvailability claudeApi vertexAi /> |

75| [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) | Control computer interfaces by taking screenshots and issuing mouse and keyboard commands. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAwsBeta bedrockBeta vertexAi azureAiBeta /> |

76| [Memory](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool) | Enable Claude to store and retrieve information across conversations. Build knowledge bases over time, maintain project context, and learn from past interactions. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

77| [Text editor](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool) | Create and edit text files with a built-in text editor interface for file manipulation tasks. | ZDR eligible | <PlatformAvailability claudeApi claudePlatformAws bedrock vertexAi azureAi /> |

7878

7979## Tool infrastructure

8080

manage-claude/admin-api Changed · +4 / -4 lines

from line 90

9090

9191| Role | Permissions |

9292| ------------------ | ------------------------------------------------------------------------------ |

93| user | Can use Playground |

94| claude\_code\_user | Can use Playground and [Claude Code](https://code.claude.com/docs/en/overview) |

95| developer | Can use Playground and manage API keys |

96| billing | Can use Playground and manage billing details |

93| user | Can use playground |

94| claude\_code\_user | Can use playground and [Claude Code](https://code.claude.com/docs/en/overview) |

95| developer | Can use playground and manage API keys |

96| billing | Can use playground and manage billing details |

9797| admin | Can do all of the preceding, plus manage users |

9898

9999Organization owners and primary owners have all admin permissions and can additionally manage admins. All references to the admin role on this page also apply to owners and primary owners.

manage-claude/cmek Changed · +5 / -5 lines

from line 41

4141

4242CMEK is currently available in US regions only, and all encryption operations are processed in US regions.

4343

44On [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), CMEK is available with AWS KMS keys only; Google Cloud KMS and Azure Key Vault keys cannot be registered. Create, validate, and attach keys in the Claude Console; the `external_keys` API endpoints are not currently available on Claude Platform on AWS. The key must be in the same AWS region as the workspace it is attached to.

44On [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), CMEK is available with AWS KMS keys only; Google Cloud KMS and Azure Key Vault keys cannot be registered. Create and attach keys in the Claude Console; the `external_keys` API endpoints are not currently available on Claude Platform on AWS. There is no separate validation step. The key policy is first exercised when a workspace starts using the key, so a key policy problem surfaces at that point rather than at registration. The key must be in the same AWS region as the workspace it is attached to.

4545

4646For minimal latency, choose a region close to Anthropic's US infrastructure:

4747

from line 68

6868* Chat attachments and project attachments.

6969* Claude Code on the CLI, including message content.

7070* Cowork in Claude Desktop.

71* Compliance API [local session transcripts](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions) captured from sessions on users' machines. If your key cannot be used, the messages endpoint returns [503 Service Unavailable](https://platform.claude.com/docs/en/manage-claude/compliance-errors#local-sessions-temporarily-unavailable) instead of transcript content. Session metadata is still listed.

7172* Office agents.

7273* Claude in Chrome.

7374

from line 82

8182

8283* Playground in the Claude Console is disabled.

8384* Portions of the Compliance API that return raw content, such as prompts, responses, and files, are disabled.

84* Other beta and research preview features may not be covered by CMEK.

85* Other beta and research preview features might not be covered by CMEK.

8586

8687**Claude Enterprise**

8788

from line 91

9091* Certain analytics are degraded: admin analytics for claude.ai skills and connectors (under claude.ai/analytics/usage and through the [Claude Enterprise Analytics API](https://platform.claude.com/docs/en/manage-claude/analytics-api)), Claude smart reports (under claude.ai/analytics/insights), and Claude Code contribution metrics (under claude.ai/analytics/claude-code).

9192* Audit log exports are disabled.

9293* Signed URLs for temporary file exchanges are disabled. These back organization data exports in claude.ai and Claude Code Remote file flows such as screenshot updates.

93* Compliance API [local session transcripts](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions) (Cowork and Claude Code on users' machines) currently return no message content. Session metadata is listed as usual, and the local session messages endpoint (`GET /v1/compliance/apps/sessions/local/{session_id}/messages`) returns each message with its content marked unavailable; see [Retrieve a local session transcript](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-a-local-session-transcript) for the response shape.

9494

9595### Encrypted with Anthropic key

9696

from line 106

106106**Claude Enterprise**

107107

108108* Claude Code Desktop, Claude Code on the web, and Claude in Slack. Anthropic recommends disabling any of these that are not appropriate for your use case in the admin console.

109* Beta and research preview features may not be covered by CMEK and can break in CMEK organizations, for example, Claude Security and Claude Design.

109* Beta and research preview features might not be covered by CMEK and can break in CMEK organizations, for example, Claude Security and Claude Design.

110110* On-demand data export under **Settings** > **Privacy**.

111111* [Personal preferences - Instructions for Claude section](https://claude.ai/new#settings/general) and Cowork Global instructions. These are set at the account level and shared across all of a user's organizations.

112112

from line 146

146146* **No retroactive encryption:** CMEK only protects data written after your key takes effect (see [How it works](https://platform.claude.com/docs/en/manage-claude/cmek#how-it-works)).

147147* **Latency:** Operations that wrap or unwrap data keys make a round-trip to your key management service, which can add a small amount of latency to actions that read or write data at rest.

148148* **Revocation delay:** Key revocation can take up to 1 hour (the cache TTL). Requests already in flight during that window may continue to succeed.

149* **KMS costs:** CMEK requires a key in a third-party key management service (AWS KMS, Google Cloud KMS, or Azure Key Vault), which may incur separate charges billed by your KMS provider.

149* **KMS costs:** CMEK requires a key in a third-party key management service (AWS KMS, Google Cloud KMS, or Azure Key Vault), which might incur separate charges billed by your KMS provider.

150150

151151## Configure your provider

152152

manage-claude/compliance-content-data Changed · +21 / -12 lines

from line 14

1414 **Prerequisite:** None for listing chats organization-wide. To filter the chat list to specific users, you need user IDs from [List organization users](https://platform.claude.com/docs/en/manage-claude/compliance-org-data#list-organization-users). The other endpoints on this page take resource IDs directly.

1515</Check>

1616

17The endpoints on this page expose Claude Enterprise chat content, file uploads, projects, and project attachments to compliance reviewers. They support eDiscovery (electronic discovery) exports, data loss prevention (DLP) enforcement, and account-deletion responses. Chat, file, and project content is retained for as long as your organization's retention policy allows. Chats that a user has soft-deleted in claude.ai remain visible through the Compliance API with `deleted_at` populated; chats that have been hard-deleted (through the Compliance API itself, or after the organization's retention window expires) are not retrievable.

17The endpoints on this page expose Claude Enterprise chat content, file uploads, projects, and project attachments to compliance reviewers. They support eDiscovery (electronic discovery) exports, data loss prevention (DLP) enforcement, and account-deletion responses. Chat, file, and project content is retained for as long as your organization's retention policy allows. When a user deletes a chat in claude.ai, its message content, attached files, tool-generated files, and artifacts are deleted with it. The Compliance API still lists the chat, with `deleted_at` populated and an empty `name`, and returns its messages without their content. Chats that have been hard-deleted (through the Compliance API itself, or after the organization's retention window expires) are not retrievable.

1818

1919Both scopes are granted only on Compliance Access Keys (`sk-ant-api01-...`) created in claude.ai; see [Set up the Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api-access) to provision one. The `read:compliance_user_data` scope covers retrieval; `delete:compliance_user_data` is required only for the delete endpoints. The chat, file, project, and attachment endpoints are not available to Admin API keys (`sk-ant-admin01-...`); calls authenticated with an Admin API key return [403 Forbidden](https://platform.claude.com/docs/en/manage-claude/compliance-errors#403-forbidden).

2020

from line 24

2424

2525Use [List chats](https://platform.claude.com/docs/en/api/compliance/apps/chats/list) to page through chat metadata, then [Get chat messages](https://platform.claude.com/docs/en/api/compliance/apps/chats/messages/list) to fetch the full message content of one chat.

2626

27The chat list endpoint defaults to organization-wide scope: leave off `user_ids[]` to include every chat under your parent organization. Add `order_by=updated_at` to sort by last update time. This combination is the recommended way to export chats and keep an export current, because one paginated loop picks up both new and modified chats for every user without enumerating users first. The following request lists chats updated since a given date.

27The chat list endpoint defaults to organization-wide scope: leave off `user_ids[]` to include every chat under your parent organization. Add `order_by=updated_at` to sort by last update time. This combination is the recommended way to export chats and keep an export current, because one paginated loop picks up new chats, modified chats, and chats deleted in claude.ai for every user without enumerating users first. The following request lists chats updated since a given date.

2828

2929```bash cURL

3030curl --fail-with-body -sS -G \

from line 62

6262

6363Results sort ascending by the `order_by` field, oldest first, with ties broken by `id`. Pagination uses the standard `first_id`/`last_id`/`has_more` cursor fields described in [Paginate results](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed#paginate-results). To walk forward toward newer chats, pass the response's `last_id` back as `after_id` on the next request.

6464

65That forward walk is also how you keep an export current across runs: persist the final page's `last_id` and resume from it as `after_id` on the next run. Because the list is ordered by `updated_at`, a chat that changes after your saved cursor reappears ahead of it, so each incremental run returns both brand-new chats and older chats that have since been modified. Process results idempotently, keyed by chat `id`, to handle those reappearances.

65That forward walk is also how you keep an export current across runs: persist the final page's `last_id` and resume from it as `after_id` on the next run. Because the list is ordered by `updated_at`, a chat that changes after your saved cursor reappears ahead of it, so each incremental run returns both brand-new chats and older chats that have since been modified or deleted in claude.ai. Process results idempotently, keyed by chat `id`, to handle those reappearances. A chat that comes back with `deleted_at` populated has no content left to fetch, so treat it as deleted rather than updated.

6666

6767A few constraints apply to these organization-wide queries. Cursors are opaque and bound to the sort key, so an `after_id` issued under one `order_by` value is rejected with a 400 error under the other. Time-filter bounds must match the sort key too: pair `updated_at.*` bounds with `order_by=updated_at`, and `created_at.*` bounds with the default `order_by=created_at`. Backward pagination with `before_id` is not supported, and the `project_ids[]` filter is not available. See [List chats](https://platform.claude.com/docs/en/api/compliance/apps/chats/list) for the full filter reference.

6868

from line 119

119119 {

120120 "id": "claude_file_01UaT9wBcDfGhJkLmNpQrSv7",

121121 "filename": "dashboard_mockup_v1.pdf",

122 "mime_type": "application/pdf"

122 "mime_type": "application/pdf",

123 "size_bytes": 482133,

124 "md5": "56367e4d2705cc9c025ad07424e944f0",

125 "created_at": "2026-04-10T08:09:10Z"

123126 }

124127 ]

125128 },

from line 140

137140 {

138141 "id": "claude_gen_file_01TbR8wAcCeFhJkLnPqStUvX",

139142 "filename": "requirements_summary.csv",

140 "mime_type": "text/csv"

143 "mime_type": "text/csv",

144 "size_bytes": 2048,

145 "md5": "89968669461d95416549937168269d6b"

141146 }

142147 ],

143148 "artifacts": [

from line 161

156161}

157162```

158163

159`files`, `generated_files`, and `artifacts` can each be `null` on a given message. `files` are binary uploads (PDFs, images, spreadsheets) the user attached to the message. `generated_files` are binary files the assistant created during the conversation through tool use (for example, PDFs, spreadsheets, or slide decks). `artifacts` are versioned documents (for example, code or markdown) the assistant generated or updated in its response; an artifact can be revised across multiple assistant turns in the same chat, and each revision appears as a new `version_id` under the same artifact `id`. Pass each entry's `id` (or `version_id` for artifacts) to the matching content endpoint in [Retrieve files and artifacts](https://platform.claude.com/docs/en/manage-claude/compliance-content-data#retrieve-files-and-artifacts) to download it.

164`files`, `generated_files`, and `artifacts` can each be `null` on a given message. `files` are the files and text attachments (for example, PDFs, images, spreadsheets, documents, and pasted text) the user attached to the message, as claude.ai stored them. `generated_files` are binary files the assistant created during the conversation through tool use (for example, PDFs, spreadsheets, or slide decks). `artifacts` are versioned documents (for example, code or markdown) the assistant generated or updated in its response; an artifact can be revised across multiple assistant turns in the same chat, and each revision appears as a new `version_id` under the same artifact `id`. Pass each entry's `id` (or `version_id` for artifacts) to the matching content endpoint in [Retrieve files and artifacts](https://platform.claude.com/docs/en/manage-claude/compliance-content-data#retrieve-files-and-artifacts) to download it.

160165

161166## Retrieve files and artifacts

162167

from line 171

166171

167172| You have | You want | Use this endpoint |

168173| ------------------------------ | --------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- |

169| `claude_file_*` ID | The file's binary content | [Download file content](https://platform.claude.com/docs/en/api/compliance/apps/chats/files/download) |

174| `claude_file_*` ID | The file's content | [Download file content](https://platform.claude.com/docs/en/api/compliance/apps/chats/files/download) |

170175| `claude_file_*` ID | The file's metadata only | [Get file metadata](https://platform.claude.com/docs/en/api/compliance/apps/chats/files/retrieve) |

171176| `claude_gen_file_*` ID | A tool-generated file's binary content | [Download a Claude-generated file](https://platform.claude.com/docs/en/api/compliance/apps/chats/generated_files/download) |

172177| `claude_gen_file_*` ID | A tool-generated file's metadata only | [Get generated-file metadata](https://platform.claude.com/docs/en/api/compliance/apps/chats/generated_files/retrieve) |

from line 180

175180| `claude_proj_doc_*` ID | A project document's plain-text content | [Get project document content](https://platform.claude.com/docs/en/api/compliance/apps/projects/documents/retrieve) |

176181| `claude_proj_doc_*` ID | A project document's metadata only | [Get project document metadata](https://platform.claude.com/docs/en/api/compliance/apps/projects/documents/metadata) |

177182

178The file content endpoint streams the original upload as a chunked binary response with these headers:

183The file content endpoint streams the content that claude.ai stored for the file as a chunked binary response. That content is not always identical to the file the user uploaded. Images can be served as a processed copy rather than the uploaded bytes. Some documents attached to chats (for example, Word files, PowerPoint files, and some PDFs) are stored as the text claude.ai extracted from them. For these documents, the endpoint returns the extracted text under the original file name, and the original document is not available through the Compliance API. The `size_bytes` and `md5` fields describe the stored content rather than the uploaded file. The file name and `mime_type` can still name the uploaded document's format. Identify a file's format from the returned bytes, not from its name or declared type.

179184

185The response carries these headers:

186

180187* `Content-Disposition: attachment; filename*=utf-8''<percent-encoded filename>` carries the original upload file name in RFC 5987 extended form. The extended form is used for every file name, not only non-ASCII ones.

181* `Content-Type` carries the upload's MIME type.

182* `Content-MD5` carries the file's MD5 digest, base64-encoded as specified in RFC 1864.

188* `Content-Type` carries the MIME type recorded for the stored content, which for a document stored as extracted text can still name the original document format.

189* `Content-MD5` carries the MD5 digest of the served bytes, base64-encoded as specified in RFC 1864.

183190* `Transfer-Encoding: chunked` is always set.

184191

185192```bash cURL

from line 216

209216

210217A project attachment is one of two distinct shapes, identified by the `type` discriminator on each entry:

211218

212Entries with `type` of `project_file` are binary uploads (PDFs, images, spreadsheets) whose IDs start with `claude_file_`; download them with [Download file content](https://platform.claude.com/docs/en/api/compliance/apps/chats/files/download). Entries with `type` of `project_doc` are plain-text documents (always `text/plain`) whose IDs start with `claude_proj_doc_`; fetch them with [Get project document content](https://platform.claude.com/docs/en/api/compliance/apps/projects/documents/retrieve).

219Entries with `type` of `project_file` are file uploads (PDFs, images, spreadsheets) whose IDs start with `claude_file_`; download them with [Download file content](https://platform.claude.com/docs/en/api/compliance/apps/chats/files/download). Entries with `type` of `project_doc` are plain-text documents (always `text/plain`) whose IDs start with `claude_proj_doc_`, including documents such as Word files that claude.ai converts to text when they are added to a project; fetch them with [Get project document content](https://platform.claude.com/docs/en/api/compliance/apps/projects/documents/retrieve).

213220

214221A consumer that walks the attachment list must branch on `type` and call the matching content endpoint for each entry. The following request lists one page of attachments; paginate by passing `next_page` back as the `page` parameter until `has_more` is `false`.

215222

from line 236

229236 "created_at": "2026-04-10T08:09:10Z",

230237 "filename": "dashboard_mockup_v1.pdf",

231238 "mime_type": "application/pdf",

239 "size_bytes": 482133,

240 "md5": "56367e4d2705cc9c025ad07424e944f0",

232241 "type": "project_file"

233242 },

234243 {

from line 259

250259 Every successful delete is permanent and immediate. There is no recovery window.

251260</Warning>

252261

253The Compliance API exposes hard-delete endpoints for chats, files, project documents, and entire projects. A hard-deleted chat cannot be restored, and it stops appearing in list responses afterward (whereas a chat soft-deleted from claude.ai still appears with `deleted_at` populated).

262The Compliance API exposes hard-delete endpoints for chats, files, project documents, and entire projects. A hard-deleted chat cannot be restored, and it stops appearing in list responses afterward.

254263

255264* [Delete chat](https://platform.claude.com/docs/en/api/compliance/apps/chats/delete): also removes the chat's messages and any files attached to those messages.

256265* [Delete file](https://platform.claude.com/docs/en/api/compliance/apps/chats/files/delete): handles both chat files and project files.

manage-claude/compliance-errors Changed · +17 / -7 lines

from line 36

3636| [409 Conflict](https://platform.claude.com/docs/en/manage-claude/compliance-errors#409-conflict) | No | The request conflicts with the resource's current state; resolve the conflict (such as detaching child resources), then retry. |

3737| [429 Too Many Requests](https://platform.claude.com/docs/en/manage-claude/compliance-errors#429-too-many-requests) | Yes, after `retry-after` | Wait the seconds in `retry-after`, then retry; do not advance your cursor. |

3838| [500 Internal Server Error](https://platform.claude.com/docs/en/manage-claude/compliance-errors#500-internal-server-error) | Depends on `x-should-retry` | Check the `x-should-retry` response header before retrying. |

39| [502, 503, 504, 529](https://platform.claude.com/docs/en/manage-claude/compliance-errors#500-internal-server-error) | Yes, with backoff | Transient; retry with exponential backoff. Exception: one local session 503 is data-dependent and can persist; see [Local sessions temporarily unavailable](https://platform.claude.com/docs/en/manage-claude/compliance-errors#local-sessions-temporarily-unavailable). |

39| [502, 503, 504, 529](https://platform.claude.com/docs/en/manage-claude/compliance-errors#500-internal-server-error) | Yes, with backoff | Transient; retry with exponential backoff. Exception: some local session 503s are not transient. See [Local sessions temporarily unavailable](https://platform.claude.com/docs/en/manage-claude/compliance-errors#local-sessions-temporarily-unavailable). |

4040

4141## 400 Bad Request

4242

from line 90

9090

9191The directory, project, and session endpoints (organizations, users, roles, role permissions, groups, group members, projects, project attachments, local and remote sessions, and session messages) paginate with an opaque `page` token rather than `after_id` and `before_id`. The same advice applies: pass the `next_page` value from the previous response unchanged, and stop when `has_more` is `false` (or, on the session endpoints, which return no `has_more`, when `next_page` is `null`). A malformed `page` token returns the same 400 `invalid_request_error` as a malformed `after_id` or `before_id`.

9292

93The two paginated local session endpoints (the list and the messages endpoint) return the following 400 `invalid_request_error` for any `page` value they cannot decode, for example a token that was truncated or altered after you stored it, or one issued by a different endpoint or under a different parent organization. On the local session messages endpoint (`GET /v1/compliance/apps/sessions/local/{session_id}/messages`), each `page` cursor is also bound to the session and `order` it was issued for, so a cursor issued for a different session or sort order returns the same body:

93The two paginated local session endpoints (the list and the messages endpoint) return the following 400 `invalid_request_error` for any `page` value they cannot decode, for example, a token that was truncated or altered after you stored it, or one issued by a different endpoint or under a different parent organization. On the local session messages endpoint (`GET /v1/compliance/apps/sessions/local/{session_id}/messages`), each `page` cursor is also bound to the session and `order` it was issued for, so a cursor issued for a different session or sort order returns the same body:

9494

9595```text wrap

9696The page parameter is not a valid cursor for this request.

from line 205

205205Chat claude_chat_01H5CWunD7RpVJ5bHa8RCkja not found.

206206```

207207

208**Cause:** The chat ID in the path does not match a chat readable through the Compliance API. The chat might have been hard-deleted through a previous Compliance API call or removed by your organization's retention policy, or it might belong to an organization the calling key cannot read. Chats that a user soft-deleted in claude.ai do not return 404; they remain readable with `deleted_at` populated.

208**Cause:** The chat ID in the path does not match a chat readable through the Compliance API. The chat might have been hard-deleted through a previous Compliance API call or removed by your organization's retention policy, or it might belong to an organization the calling key cannot read. Chats that a user deleted in claude.ai do not return 404; they remain readable, with `deleted_at` populated, but without their message content.

209209

210210**Fix:** Confirm the chat ID against a recent `claude_chat_created` or `claude_chat_viewed` activity. If the activity is recent and the read still fails, the chat has been hard-deleted (through this API or by retention-policy expiry) or belongs to an organization outside your key's scope.

211211

from line 357

357357

358358A 500 from the Compliance API carries an `x-should-retry: false` response header when the failure is deterministic. Anthropic SDKs honor this header automatically. If you use a generic HTTP retry library that retries on every 5xx, suppress retries when `x-should-retry` is `false`; retrying this error fails identically on every attempt.

359359

360A 500 without the `x-should-retry: false` header is transient: retry with exponential backoff (start at 1 second, double up to 60 seconds). The same applies to 502, 503, 504, and 529 responses. One local session 503, described next, is data-dependent rather than transient. See [Errors](https://platform.claude.com/docs/en/api/errors) for the platform-wide retry semantics.

360A 500 without the `x-should-retry: false` header is transient: retry with exponential backoff (start at 1 second, double up to 60 seconds). The same applies to 502, 503, 504, and 529 responses. The exception is a small set of local session 503s, described next, that depend on an organization's settings or encryption key rather than on load. See [Errors](https://platform.claude.com/docs/en/api/errors) for the platform-wide retry semantics.

361361

362362### Local sessions temporarily unavailable

363363

from line 375

375375The local-sessions index cannot currently evaluate retention overrides for this page. Try again later.

376376```

377377

378**Cause:** The [local session endpoints](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions) return 503 with one of these bodies. The first two mean that session listings, or a session's captured content, are briefly unavailable; that is a transient condition related to load or to the back end. The third body (which reads `for this session` instead of `for this page` on the retrieve and messages endpoints) means that a retention or data-handling setting that applies to one or more sessions in the requested range could not yet be evaluated. That depends on the data and settings of the organization that ran the session rather than on load, and it can persist for an extended period. All three bodies share the `overloaded_error` type, so this is one of the few cases on this page where the message text, rather than `error.type`, distinguishes conditions that need different handling.

378**Cause:** The [local session endpoints](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions) return 503 with one of these bodies. All three share the `overloaded_error` type, so this is one of the few errors on this page where you need the message text, not `error.type`, to tell the conditions apart:

379379

380**Fix:** For the two `Try again shortly.` bodies, retry with exponential backoff and do not advance your `page` cursor, because the failed request returned no data. For the `Try again later.` body, do not hold a walk open waiting for it to clear. On the list endpoint, either retry later by restarting without the `page` parameter (a list page token older than 24 hours is still accepted but is re-evaluated against the current retention boundary, so a parked walk can skip sessions), or narrow the `created_at.gte` and `created_at.lt` window until the request succeeds and export the skipped range separately on a later run. On the retrieve and messages endpoints, skip that session ID, continue with the rest of your export, and retry the session on a later run; messages page cursors expire 24 hours after the walk's first page, so restart that session's walk without `page` when you return to it. If the condition recurs across runs, contact your Anthropic representative and include the `request-id` response header.

380* The `index is temporarily unavailable` body means session listings are briefly unavailable because of load or a back-end condition. This is transient.

381* The `Captured content` body means a session's transcript content cannot be returned right now. This is usually transient too. In organizations that use [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek), the messages endpoint also returns this body for every page that contains content your key cannot decrypt, for example because you disabled, revoked, or destroyed the key, or because the key cannot be reached. In that case the error persists for as long as the key cannot be used. The message text is the same either way, so the only signal that the key is the cause is that the error keeps recurring for that organization. An unusable key is never reported as `not_captured`.

382* The `retention overrides` body means a retention or data-handling setting that applies to one or more sessions in the requested range could not be evaluated yet. On the retrieve and messages endpoints it reads `for this session` instead of `for this page`. It depends on the data and settings of the organization that ran the session rather than on load, and it can persist for an extended period.

383

384**Fix:** Handle each body as follows:

385

386* For the two `Try again shortly.` bodies, retry with exponential backoff and do not advance your `page` cursor, because the failed request returned no data.

387* If the `Captured content` body keeps recurring on the messages endpoint for an organization that uses a customer-managed key, treat it as persistent: stop walking that organization's transcripts and check the key's status in your key management service. Transcripts in other linked organizations, and session metadata everywhere, are unaffected. If you retry on a later run, restart each session's walk without `page`, because messages page cursors expire 24 hours after the walk's first page.

388* For the `Try again later.` body, do not hold a walk open waiting for it to clear. On the list endpoint, either retry later by restarting without the `page` parameter (a list page token older than 24 hours is still accepted but is re-evaluated against the current retention boundary, so a parked walk can skip sessions), or narrow the `created_at.gte` and `created_at.lt` window until the request succeeds and export the skipped range separately on a later run. On the retrieve and messages endpoints, skip that session ID, continue with the rest of your export, and retry the session on a later run. Messages page cursors expire 24 hours after the walk's first page, so restart that session's walk without `page` when you return to it.

389

390If any of these conditions recurs across runs, contact your Anthropic representative and include the `request-id` response header. For the customer-managed key case, do this only if the error continues while your key is usable.

381391

382392For service-wide incidents, check [status.anthropic.com](https://status.anthropic.com).

383393

manage-claude/compliance-faq Changed · +4 / -4 lines

from line 60

6060

6161<AccordionGroup>

6262 <Accordion title="How far back does the Activity Feed go?">

63 The Activity Feed retains 6 years of organization activity, and new events are queryable within 1 minute of occurring. The feed reaches back at most to the point the Compliance API was first enabled for your organization: recording is not retroactive, and activity from before enablement is not backfilled. Activity Feed retention is independent of your organization's content retention policy: chat, file, and project content follows the retention rules configured for your organization (indefinite by default).

63 The Activity Feed retains 6 years of organization activity, and new events are queryable within 1 minute of occurring. The feed reaches back at most to the point the Compliance API was first enabled for your organization: recording is not retroactive, and activity from before enablement is not backfilled. Activity Feed retention is independent of your organization's content retention policy: chat, file, and project content follows the retention rules configured for your organization (indefinite by default), unless a user deletes it sooner.

6464 </Accordion>

6565

6666 <Accordion title="Does the Activity Feed include prompt or message content?">

from line 103

103103 </Accordion>

104104

105105 <Accordion title="Is deleted content recoverable through the Compliance API?">

106 No. Deletes performed through the Compliance API are immediate, permanent, and not recoverable. Chats that a user deleted through claude.ai are soft-deleted: they remain visible through the Compliance API with `deleted_at` populated until your organization's retention window expires or you hard-delete them through this API. Pull any content you need to retain (for legal hold or archival) before issuing a `DELETE` request.

106 No. Deletes performed through the Compliance API are immediate, permanent, and not recoverable. The content of a chat that a user deletes in claude.ai is not recoverable either: the Compliance API still returns the chat and its messages, with `deleted_at` populated, but not their content. Pull any content you need to retain (for legal hold or archival) while it is still available. See [Plan content retention](https://platform.claude.com/docs/en/manage-claude/compliance-integration-patterns#plan-content-retention) for when to export content to your own archive.

107107 </Accordion>

108108

109109 <Accordion title="What does the Compliance API not capture?">

110 The Compliance API has known coverage boundaries: the Activity Feed records resource events but not prompt or response text, Claude Console and Claude API workloads authenticated with an API key expose no message content at all, and content removed by your retention policy or by a hard delete is not recoverable. For the full coverage boundaries and delivery contract, see [Delivery guarantees and completeness](https://platform.claude.com/docs/en/manage-claude/compliance-integration-patterns#delivery-guarantees-and-completeness).

110 The Compliance API has known coverage boundaries: the Activity Feed records resource events but not prompt or response text, Claude Console and Claude API workloads authenticated with an API key expose no message content at all, and content removed by your retention policy, deleted by a user in claude.ai, or hard-deleted through the Compliance API is not recoverable. For the full coverage boundaries and delivery contract, see [Delivery guarantees and completeness](https://platform.claude.com/docs/en/manage-claude/compliance-integration-patterns#delivery-guarantees-and-completeness).

111111

112 Cowork and Claude Code session transcripts have boundaries of their own. Local sessions are captured only as their requests reach the Claude API, so on-device activity that never reaches the API is not captured. Claude Code sessions authenticated with a Claude Console API key, Claude Code sessions run through a third-party cloud platform (Amazon Bedrock, Google Cloud, or Microsoft Foundry), and Claude Code on the web are not captured either; organizations with HIPAA readiness enabled get no local session data; and sessions for which zero data retention is in effect are excluded. No session transcript, local or remote, includes thinking blocks or tool definitions. Organizations that use [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek) see local session metadata but no transcript content.

112 Cowork and Claude Code session transcripts have boundaries of their own. Local sessions are captured only as their requests reach the Claude API, so on-device activity that never reaches the API is not captured. Claude Code sessions authenticated with a Claude Console API key, Claude Code sessions run through a third-party cloud platform (Amazon Bedrock, Google Cloud, or Microsoft Foundry), and Claude Code on the web are not captured either; organizations with HIPAA readiness enabled get no local session data; and sessions for which zero data retention is in effect are excluded. No session transcript, local or remote, includes thinking blocks or tool definitions. Organizations that use [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek) receive local session transcripts as usual. While the key cannot be used, the messages endpoint returns [503 Service Unavailable](https://platform.claude.com/docs/en/manage-claude/compliance-errors#local-sessions-temporarily-unavailable) instead of transcript content, and session metadata is still listed.

113113 </Accordion>

114114</AccordionGroup>

115115

manage-claude/compliance-integration-patterns Changed · +6 / -3 lines

from line 113

113113| Data | Retained for | Controlled by |

114114| ------------------------------------------------------- | -------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------- |

115115| Activity Feed records | 6 years | Anthropic |

116| Chat, file, and project content | Your organization's claude.ai retention policy | Your organization |

116| Chat, file, and project content | Your organization's claude.ai retention policy, unless a user deletes it sooner | Your organization |

117117| Local session transcripts (sessions on users' machines) | 6 years by default, or your organization's custom conversation retention period when a finite one is set | Anthropic by default; your organization when it sets a custom period |

118118| Remote session transcripts (sessions in the cloud) | 6 years | Anthropic |

119119| Content hard-deleted through the Compliance API | Not retained; deletion is immediate and permanent | The caller of the `DELETE` endpoint |

from line 124

124124

125125* If your legal-hold or audit horizon exceeds 6 years for activity metadata or session transcripts, export Activity Feed pages and session transcripts to your own archive as you ingest them.

126126* If your content-retention policy is shorter than your eDiscovery horizon, export chat and file content before the retention window expires; the Compliance API cannot return content that retention has already removed. The same applies to local session transcripts, which follow your organization's custom conversation retention period when a finite one is set, even when that period is shorter than 6 years. The local session endpoints stop returning messages older than your organization's current period as soon as the setting changes, and lengthening the period later does not restore transcripts that have already expired, so export any transcript you must keep beyond it.

127* If a workflow might issue a Compliance API hard-delete (for example, DLP enforcement), retrieve and archive the target content first. There is no recovery window after a hard-delete; soft-deletes from claude.ai remain retrievable with `deleted_at` populated, but Compliance API deletes do not.

127* If you must retain chat content after users delete it in claude.ai (for example, under a legal hold), export chat, file, and artifact content to your own archive as you ingest it; the Compliance API cannot return content that a user has already deleted.

128* If a workflow might issue a Compliance API hard-delete (for example, DLP enforcement), retrieve and archive the target content first. There is no recovery window after a hard-delete.

128129

129130In every other case, rely on direct API retrieval and avoid maintaining a parallel copy.

130131

from line 148

147148* Claude Code usage authenticated with a Claude Console API key, run through a third-party cloud platform (Amazon Bedrock, Google Cloud, or Microsoft Foundry), or run in Claude Code on the web.

148149* Local sessions from organizations with [HIPAA readiness](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#hipaa-readiness) enabled, and local sessions for which [zero data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#zero-data-retention-zdr-scope) is in effect.

149150* Thinking blocks, and images or other binary content, inside session transcripts (transcripts carry user prompts, assistant responses, and tool activity only; local session transcripts show a placeholder `text` block where binary content was omitted).

151* The original file for a chat attachment that claude.ai stored as extracted text, such as some Word, PowerPoint, and PDF uploads (the file content endpoint returns the extracted text; see [Retrieve files and artifacts](https://platform.claude.com/docs/en/manage-claude/compliance-content-data#retrieve-files-and-artifacts)).

150152* The system prompt of local sessions (a marker message stands in for it).

151153* Tool definitions and MCP server configuration in session transcripts (local or remote), and citation metadata on `text` blocks in local session transcripts.

152* Transcript content for local sessions in organizations that use [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek) (session metadata is still listed).

154* Local session transcript content in an organization whose [customer-managed encryption key](https://platform.claude.com/docs/en/manage-claude/cmek) cannot currently be used. Those requests return [503 Service Unavailable](https://platform.claude.com/docs/en/manage-claude/compliance-errors#local-sessions-temporarily-unavailable), and session metadata is still listed.

153155* Content removed by your organization's retention policy.

156* Content of chats that users delete in claude.ai (the chats are still listed, with `deleted_at` populated).

154157* Content hard-deleted through the Compliance API.

155158

156159See the [Compliance API FAQ](https://platform.claude.com/docs/en/manage-claude/compliance-faq#data-coverage-and-retention) for more on what the Compliance API does and does not capture.

manage-claude/compliance-sessions Changed · +4 / -4 lines

from line 58

5858

5959For local sessions, Anthropic records each conversation server-side as its requests reach the Claude API; nothing is installed on the device, and nothing is collected beyond the requests the client already sends to the Claude API. Local session transcripts show what Claude was asked to do and what it returned, not what happened on the device. File and network activity is visible only through the tool calls and tool results in the transcript, so activity that never reaches the API (for example, local files the session never sent) is not captured.

6060

61In organizations that use [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek), local sessions are listed and retrievable as usual, but transcript content is not currently returned; each message comes back with its content marked unavailable (see [Retrieve a local session transcript](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-a-local-session-transcript) for how such messages are marked).

61In organizations that use [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek), local session transcripts are encrypted under your key and returned as usual. While your key cannot be used (for example, because you disabled or revoked it, or because it cannot be reached), the messages endpoint returns [503 Service Unavailable](https://platform.claude.com/docs/en/manage-claude/compliance-errors#local-sessions-temporarily-unavailable) for the affected pages instead of transcript content. Those messages are never reported as `not_captured` (see [Retrieve a local session transcript](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-a-local-session-transcript)). Listing sessions and retrieving session metadata are not affected.

6262

6363The list endpoint returns session metadata, with no transcript content, for every linked organization your key can read. Unlike the remote session list, it has no organization or user filters: bound the results in time with the `created_at.gte` and `created_at.lt` parameters. Both take RFC 3339 timestamps with a required UTC offset, and when both are supplied, `created_at.lt` must be strictly after `created_at.gte` or the request returns [400 Bad Request](https://platform.claude.com/docs/en/manage-claude/compliance-errors#400-bad-request). A third time filter, `updated_at.gte`, bounds by last activity instead of first: it returns sessions whose last inference call is at or after the given time and combines with the `created_at` filters without changing the ordering or pagination. Use it to poll for sessions active since a previous pass, as described later in this section. New sessions and messages appear in results after a short processing delay, typically within minutes; a session that is missing immediately after it starts is not necessarily uncaptured. The following request lists sessions created since a given date.

6464

from line 108

108108

109109In each session object, `user.id` is always set and survives account deletion; `user.email_address` is `null` when the user's account has been deleted or the user is no longer a member of an organization your key can read. `workspace_id` is `null` when the session was not associated with a workspace. A local session corresponds to one client session ID: starting a new conversation in the client, or clearing its context, begins a new session record. Treat `id` values as opaque strings; the format may change without notice.

110110

111Local sessions carry an `updated_at` but no `status`: a local session has no server-side lifecycle status, and its visibility is governed by retention instead. A local session is captured as the series of Claude API calls (inference calls) that the client makes during the session, and retention applies to each captured call individually. `created_at` is the timestamp of the session's earliest retained call and `updated_at` the timestamp of its last, both UTC. As older calls age past the retention period, `created_at` advances accordingly, and once every call in a session has aged out, the session is no longer returned; `updated_at` tracks the most recent call and is unaffected until then. Because `created_at` can shift between runs, deduplicate on `id` when you re-walk the list over time. To keep transcripts current as sessions gain messages, poll with the `updated_at.gte` filter, overlapping consecutive windows. On the list endpoint `updated_at` is a lower bound: for a session still active at a page or `created_at.lt` window boundary it can momentarily lag the session's true last activity, and a new call only becomes queryable after the short processing delay noted earlier. Because of that lag, set each run's `updated_at.gte` a few minutes before your previous run's start time, not to the previous run's time exactly. A bound set to the exact previous time silently and permanently drops a session whose final call was still indexing at that moment, because once the bound advances past that call no later run returns it. Deduplicate the returned sessions on `id`, re-fetch their transcripts, and deduplicate messages on `id`. Retrieving a session, or its messages, always reflects the exact latest retained call, so a periodic reconciliation pass over an older window is the belt-and-braces alternative to widening the overlap.

111Local sessions carry an `updated_at` but no `status`: a local session has no server-side lifecycle status, and its visibility is governed by retention instead. A local session is captured as the series of Claude API calls (inference calls) that the client makes during the session, and retention applies to each captured call individually. `created_at` is the timestamp of the session's earliest retained call and `updated_at` the timestamp of its last, both UTC. As older calls age past the retention period, `created_at` advances accordingly, and once every call in a session has aged out, the session is no longer returned; `updated_at` tracks the most recent call and is unaffected until then. Because `created_at` can shift between runs, deduplicate on `id` when you re-walk the list over time. To keep transcripts current as sessions gain messages, poll with the `updated_at.gte` filter, overlapping consecutive windows. On the list endpoint `updated_at` is a lower bound: for a session still active at a page or `created_at.lt` window boundary it can momentarily lag the session's true last activity, and a new call only becomes queryable after the short processing delay noted earlier. Because of that lag, set each run's `updated_at.gte` a few minutes before your previous run's start time, not to the previous run's time exactly. A bound set to the exact previous time silently and permanently drops a session whose final call was still indexing at that moment, because once the bound advances past that call no later run returns it. Deduplicate the returned sessions on `id`, re-fetch their transcripts, and deduplicate messages on `id`. Retrieving a session, or its messages, always reflects the exact latest retained call, so a periodic reconciliation pass over an older window is a more thorough alternative to widening the overlap.

112112

113113The list is built from session activity metadata, so it can include sessions whose transcript content was not captured, for example sessions that ran before capture began for your organization (as far back as your retention period allows); the transcript of such a session returns each message with its content marked unavailable (see [Retrieve a local session transcript](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-a-local-session-transcript)).

114114

from line 259

259259

260260Messages are returned oldest first by default; pass `order=desc` to reverse. Pagination uses the same `page`/`next_page` scheme as the list endpoint, with a `limit` default of 100 and a max of 1,000. A page can end early when the response reaches its size limit, so a page with fewer than `limit` messages does not mean you have reached the end; keep paginating until `next_page` is `null`. Page cursors are bound to the session and sort order they were issued under, and a walk's cursors expire 24 hours after its first page: an expired cursor returns [400 Bad Request](https://platform.claude.com/docs/en/manage-claude/compliance-errors#400-bad-request) telling you to restart without the `page` parameter, and the restarted walk reflects the current retention boundary. A cursor issued for a different session or `order` also returns 400, as an invalid cursor.

261261

262Each message carries a `role` (`user` or `assistant`) and a `content` array of `text`, `tool_use`, and `tool_result` blocks. It also carries a `model`: on an assistant turn captured from the Claude API this is the model that served the turn, and it is `null` on user messages and on any assistant message whose `provenance` is set, since client-asserted history and synthetic markers were not produced by a model and the serving model is unknown for unavailable content. A `text` block carries `text` and `truncated`. A `tool_use` block carries `id`, `name`, `input`, and `truncated`, where `input` is a JSON-encoded string rather than an object. A `tool_result` block carries `tool_use_id`, `name`, `is_error`, a `content` array of `text` entries, and `truncated`. MCP tool calls and results, and most server tool calls and results, are normalized into these same `tool_use` and `tool_result` shapes; any other block type appears as a `[<block type> content not shown]` placeholder. A message `id` is stable while the turn is retained. Every message reconstructed from the same inference call carries that call's timestamp, so consecutive messages often share a `created_at` value; preserve the returned order rather than re-sorting by timestamp.

262Each message carries a `role` (`user` or `assistant`) and a `content` array of `text`, `tool_use`, and `tool_result` blocks. It also carries a `model`: on an assistant turn captured from the Claude API this is the model that served the turn, and it is `null` on user messages and on any assistant message whose `provenance` is set, because client-asserted history and synthetic markers were not produced by a model and the serving model is unknown for unavailable content. A `text` block carries `text` and `truncated`. A `tool_use` block carries `id`, `name`, `input`, and `truncated`, where `input` is a JSON-encoded string rather than an object. A `tool_result` block carries `tool_use_id`, `name`, `is_error`, a `content` array of `text` entries, and `truncated`. MCP tool calls and results, and most server tool calls and results, are normalized into these same `tool_use` and `tool_result` shapes; any other block type appears as a `[<block type> content not shown]` placeholder. A message `id` is stable while the turn is retained. Every message reconstructed from the same inference call carries that call's timestamp, so consecutive messages often share a `created_at` value; preserve the returned order rather than re-sorting by timestamp.

263263

264264Each message also carries a `provenance` field describing how its content was captured. `provenance` is `null` for verified content captured by the Claude API, which is the common case. Otherwise it is an object whose `type` marks the exception:

265265

266* `content_unavailable` means the content cannot be returned. The `content` array is empty, and `provenance.reason` states why. `not_captured` means no content is available for the turn; it does not prove that no record was stored, because content withheld by a storage-side access policy is reported with the same reason (for example, in organizations that use [customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek#disabled-or-modified)), and individual turns within an otherwise captured session can be unavailable for other data-handling reasons and carry the same reason. `client_aborted` means the client closed the connection or cancelled the request before the response completed, so the turn's response was not captured; any partial output already streamed to the client is not included, and this reason applies to assistant-role turns only. `cmek_key_revoked` is reserved for content encrypted under your organization's customer-managed key when that key is unavailable (for example, revoked); it is not currently returned, so handle it for forward compatibility. `retention_elapsed` means the content aged past retention. `oversize` means a single message exceeded the per-message size bound; the message is still returned, with an empty `content` array.

266* `content_unavailable` means the content cannot be returned. The `content` array is empty, and `provenance.reason` states why. `not_captured` means no content is available for the turn. It does not prove that no record was stored: content that Anthropic's data-handling policies withhold from the Compliance API is reported with the same reason, and so are individual turns within an otherwise captured session that are unavailable for such reasons. An unusable customer-managed key is the one exception and returns [503 Service Unavailable](https://platform.claude.com/docs/en/manage-claude/compliance-errors#local-sessions-temporarily-unavailable) instead. `client_aborted` means the client closed the connection or cancelled the request before the response completed, so the turn's response was not captured; any partial output already streamed to the client is not included, and this reason applies to assistant-role turns only. `cmek_key_revoked` is reserved for content encrypted under your organization's customer-managed key when that key is unavailable (for example, revoked). It is not currently returned, because an unusable key produces a 503 instead, but handle it for forward compatibility. `retention_elapsed` means the content aged past retention. `oversize` means a single message exceeded the per-message size bound; the message is still returned, with an empty `content` array.

267267* `client_asserted` marks assistant messages that the client supplied as conversation history and that could not be matched to a captured response; their authorship is not verified.

268268* `synthetic_marker` marks records generated by the endpoint itself, such as the marker that stands in for the system prompt. When the client rewrites or compacts its conversation history mid-session (for example, after context compaction), the transcript inserts a marker message at that point and continues with the new content the client sent; when your organization has a finite retention period, the rewritten history itself is withheld (a second marker notes this) and only the latest user turn and what follows are shown.

269269

manage-claude/usage-cost-api Changed · +7 / -3 lines

### What happens with playground usage? ### What happens with Playground usage?

from line 56

5656 Agentless integration for easy LLM observability with out-of-the-box dashboards and alerts

5757 </Card>

5858

59 <Card title="Harness" icon="chart" href="https://developer.harness.io/docs/cloud-cost-management/provider-integrations/ai-providers/anthropic/">

60 FinOps platform for cloud and AI cost management

61 </Card>

62

5963 <Card title="Honeycomb" icon="polygon" href="https://docs.honeycomb.io/integrations/anthropic-usage-monitoring/">

6064 Advanced querying and visualization through OpenTelemetry

6165 </Card>

from line 314

310314

311315Filter or group by `service_tier` in the usage endpoint and look for the `priority` value. Priority Tier costs are not available in the cost endpoint.

312316

313### What happens with Playground usage?

317### What happens with playground usage?

314318

315API usage from Playground in the Claude Console (and from the legacy Workbench before it) is not associated with an API key, so `api_key_id` will be `null` even when grouping by that dimension.

319API usage from playground in the Claude Console (and from the legacy Workbench before it) is not associated with an API key, so `api_key_id` will be `null` even when grouping by that dimension.

316320

317321### How is the default workspace represented?

318322

api/overview Changed · +1 / -1 lines

from line 55

5555

5656### Getting API keys

5757

58The API is made available through the web [Console](https://platform.claude.com/). You can use [Playground](https://platform.claude.com/playground) to try out the API in the browser and then generate API keys in [Account Settings](https://platform.claude.com/settings/keys). You choose each key's [expiration](https://platform.claude.com/docs/en/manage-claude/authentication#key-expiration) when you create it. Use [workspaces](https://platform.claude.com/settings/workspaces) to segment your API keys and [control spend](https://platform.claude.com/docs/en/api/rate-limits) by use case.

58The API is made available through the web [Console](https://platform.claude.com/). You can use [playground](https://platform.claude.com/playground) to try out the API in the browser and then generate API keys in [Account Settings](https://platform.claude.com/settings/keys). You choose each key's [expiration](https://platform.claude.com/docs/en/manage-claude/authentication#key-expiration) when you create it. Use [workspaces](https://platform.claude.com/settings/workspaces) to segment your API keys and [control spend](https://platform.claude.com/docs/en/api/rate-limits) by use case.

5959

6060## Client SDKs

6161

build-with-claude/claude-on-vertex-ai Changed · +1 / -2 lines

from line 349

349349* [Messages API](https://platform.claude.com/docs/en/api/messages/create)

350350* [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching)

351351* [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking)

352* [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), including the [Bash tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool), [Computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool), [Memory tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool), and [Text editor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool)

352* [Tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), including the [Bash tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool), [Browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool), [Computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool), [Memory tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool), and [Text editor tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool)

353353* [Web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool)

354354* [Citations](https://platform.claude.com/docs/en/build-with-claude/citations)

355355* [Structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs)

from line 362

362362* API endpoints (Message Batches, Models, Admin, Compliance, Usage and Cost)

363363* Claude Managed Agents

364364* Server-side fallback (the [`fallbacks` parameter](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback); use the [client-side fallback pattern](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead)

365* [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolsets (`computer_toolset_20260801` and `browser_toolset_20260801` are not currently available on Google Cloud; the beta computer use tool versions remain available)

366365

367366### Context window

368367

build-with-claude/prompt-engineering/prompting-claude-opus-4-8 Changed · +1 / -1 lines

from line 157

157157

158158## Computer use

159159

160On the Claude API, Claude Opus 4.8 supports the `computer_toolset_20260801` toolset and the earlier `computer_20251124` tool version. For tasks inside webpages, Claude Opus 4.8 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`). [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.

160Claude Opus 4.8 supports the `computer_toolset_20260801` toolset (on the Claude API and Google Cloud) and the earlier `computer_20251124` tool version. For tasks inside webpages, Claude Opus 4.8 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`). [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.

161161

162162For particularly cost-sensitive workloads, 720p or 1366×768 are lower-cost options with strong performance. Conduct your own testing to find the ideal settings for your use case; experimenting with effort settings can also help tune the model's behavior.

163163

build-with-claude/prompt-engineering/prompting-claude-sonnet-5 Changed · +1 / -1 lines

from line 153

153153

154154## Computer use

155155

156On the Claude API, Claude Sonnet 5 supports the `computer_toolset_20260801` toolset and the earlier `computer_20251124` tool version. For tasks inside webpages, Claude Sonnet 5 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`). [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.

156Claude Sonnet 5 supports the `computer_toolset_20260801` toolset (on the Claude API and Google Cloud) and the earlier `computer_20251124` tool version. For tasks inside webpages, Claude Sonnet 5 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) (`browser_toolset_20260801`). [Computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) capability works across resolutions, up to a maximum resolution of 2576px / 3.75MP. Internal computer use testing shows that sending images at 1080p provides a good balance of performance and cost.

157157

158158For particularly cost-sensitive workloads, 720p or 1366×768 are lower-cost options with strong performance. Conduct your own testing to find the ideal settings for your use case; experimenting with effort settings can also help tune the model's behavior.

159159

home Changed · +1 / -1 lines

from line 95

9595 </HomeJourneyLink>

9696

9797 <HomeJourneyLink icon="message" href="https://platform.claude.com/playground">

98 Try the API in Playground

98 Try the API in playground

9999 </HomeJourneyLink>

100100 </HomeJourneyStep>

101101

intro Changed · +1 / -1 lines

from line 75

7575

7676<CardGroup cols={3}>

7777 <Card title="Developer Console" icon="computer" href="https://platform.claude.com/">

78 Explore and understand the API in your browser with Playground.

78 Explore and understand the API in your browser with playground.

7979 </Card>

8080

8181 <Card title="API Reference" icon="code" href="https://platform.claude.com/docs/en/api/overview">

manage-claude/api-and-data-retention Changed · +1 / -1 lines

from line 30

3030

3131### What ZDR does not cover

3232

33* **Claude Console:** Any usage in the Claude Console, including Playground.

33* **Claude Console:** Any usage in the Claude Console, including playground.

3434* **Claude Managed Agents:** Claude Managed Agents is a stateful resource; session transcripts persist until you delete them.

3535* **Claude consumer products:** Claude Free, Pro, and Max plans, including when customers on those plans use Claude's web, desktop, or mobile apps or Claude Code.

3636* **Claude Teams and Claude Enterprise product interfaces:** These interfaces are not ZDR-eligible. The exception is Claude Code used through Claude Enterprise with ZDR enabled; see [What ZDR covers](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#what-zdr-covers).

manage-claude/cmek-aws-kms Changed · +1 / -1 lines

from line 134

134134 Create an external key configuration through the Admin API.

135135

136136 <Note>

137 For organizations on [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), the external key endpoints are not yet available. Register, validate, and attach your key in the Claude Console instead.

137 For organizations on [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), the external key endpoints are not yet available. Register and attach your key in the Claude Console instead. There is no separate validation step; the key policy is first exercised when a workspace starts using the key, so a key policy problem surfaces at that point rather than at registration.

138138 </Note>

139139

140140 ```bash

manage-claude/workspaces Changed · +1 / -1 lines

from line 38

3838

3939| Role | Permissions |

4040| --------------------------- | ----------------------------------------------------------------------------------------------- |

41| Workspace User | Use Playground only |

41| Workspace User | Use playground only |

4242| Workspace Limited Developer | Create and manage API keys, use the API. Cannot access session tracing views or download files. |

4343| Workspace Developer | Create and manage API keys, use the API |

4444| Workspace Admin | Full control over workspace settings and members |

models/opus-5/migration-guide Changed · +2 / -2 lines

from line 113

113113

114114## Migrating to Claude Opus 5 from Claude Opus 4.7

115115

116Claude Opus 5 should have strong out-of-the-box performance on existing Claude Opus 4.7 prompts and evals, at the same pricing of $5 per million input tokens and $25 per million output tokens. It supports the same set of features as Claude Opus 4.7, including the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), [128k max output tokens](https://platform.claude.com/docs/en/models/overview), [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching), [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), with two exceptions: [web fetch](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool) is not available on Claude Opus 5, and [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models) is not supported on Claude Opus 5. It also adds [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) and publicly documents [refusal stop details](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response). On the Claude API, Claude Opus 5 also supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) as the stable `computer_toolset_20260801` toolset and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) for tasks inside webpages, neither of which Claude Opus 4.7 supports; existing integrations on the earlier `computer_20251124` version continue to work unchanged on both models. To upgrade an existing integration, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124).

116Claude Opus 5 should have strong out-of-the-box performance on existing Claude Opus 4.7 prompts and evals, at the same pricing of $5 per million input tokens and $25 per million output tokens. It supports the same set of features as Claude Opus 4.7, including the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), [128k max output tokens](https://platform.claude.com/docs/en/models/overview), [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching), [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview), with two exceptions: [web fetch](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool) is not available on Claude Opus 5, and [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models) is not supported on Claude Opus 5. It also adds [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) and publicly documents [refusal stop details](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response). On the Claude API and Google Cloud, Claude Opus 5 also supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) as the stable `computer_toolset_20260801` toolset and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) for tasks inside webpages, neither of which Claude Opus 4.7 supports; existing integrations on the earlier `computer_20251124` version continue to work unchanged on both models. To upgrade an existing integration, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124).

117117

118118<Note>

119119 If your code is on Claude Opus 4.6 or earlier, use [Migrating to Claude Opus 5 from Claude Opus 4.6 and earlier Opus models](https://platform.claude.com/docs/en/models/opus-5/migration-guide#migrating-from-claude-opus-46) instead. That section includes breaking changes (sampling parameters rejected, manual extended thinking rejected, new tokenizer) that the upgrade from Claude Opus 4.7 alone does not cover.

from line 234

234234* [Vision](https://platform.claude.com/docs/en/build-with-claude/vision)

235235* Server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) ([bash](https://platform.claude.com/docs/en/agents-and-tools/tool-use/bash-tool), [code execution](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool), [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool), [text editor](https://platform.claude.com/docs/en/agents-and-tools/tool-use/text-editor-tool), [web search](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool), [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector), [memory](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool))

236236

237Two exceptions: [web fetch](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool) is not available on Claude Opus 5, and [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models) is not supported on Claude Opus 5. On the Claude API, Claude Opus 5 also supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) as the stable `computer_toolset_20260801` toolset and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) for tasks inside webpages, neither of which Claude Opus 4.6 or earlier Opus models support; existing integrations on the earlier `computer_20251124` version continue to work unchanged on Claude Opus 5. To upgrade an existing integration, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124).

237Two exceptions: [web fetch](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool) is not available on Claude Opus 5, and [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models) is not supported on Claude Opus 5. On the Claude API and Google Cloud, Claude Opus 5 also supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) as the stable `computer_toolset_20260801` toolset and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) for tasks inside webpages, neither of which Claude Opus 4.6 or earlier Opus models support; existing integrations on the earlier `computer_20251124` version continue to work unchanged on Claude Opus 5. To upgrade an existing integration, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124).

238238

239239### Update your model name

240240

models/sonnet-5/migration-guide Changed · +1 / -1 lines

from line 20

2020

2121Claude Sonnet 5 offers the best combination of speed and intelligence in the Claude model family. It builds on Claude Sonnet 4.6.

2222

23Claude Sonnet 5 is a drop-in upgrade for Claude Sonnet 4.6, priced at $2/$10 USD per million input/output tokens; see [Pricing](https://platform.claude.com/docs/en/about-claude/pricing) for details. There are two breaking API changes for code already running on Claude Sonnet 4.6: manual extended thinking (`thinking: {type: "enabled", budget_tokens: N}`) and sampling parameters (`temperature`, `top_p`, `top_k`) set to non-default values are no longer accepted and return a 400 error. Use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) instead. Claude Sonnet 5 supports the same set of features as Claude Sonnet 4.6, including the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching), [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and the full set of server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). On the Claude API, Claude Sonnet 5 also supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) as the stable `computer_toolset_20260801` toolset and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) for tasks inside webpages, neither of which Claude Sonnet 4.6 supports; existing integrations on the earlier `computer_20251124` version continue to work unchanged on both models. To upgrade an existing integration, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models) is not available on Claude Sonnet 5. Claude Sonnet 5 also uses a new tokenizer.

23Claude Sonnet 5 is a drop-in upgrade for Claude Sonnet 4.6, priced at $2/$10 USD per million input/output tokens; see [Pricing](https://platform.claude.com/docs/en/about-claude/pricing) for details. There are two breaking API changes for code already running on Claude Sonnet 4.6: manual extended thinking (`thinking: {type: "enabled", budget_tokens: N}`) and sampling parameters (`temperature`, `top_p`, `top_k`) set to non-default values are no longer accepted and return a 400 error. Use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) with the [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) instead. Claude Sonnet 5 supports the same set of features as Claude Sonnet 4.6, including the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows), [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching), [batch processing](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://platform.claude.com/docs/en/build-with-claude/files), [PDF support](https://platform.claude.com/docs/en/build-with-claude/pdf-support), [vision](https://platform.claude.com/docs/en/build-with-claude/vision), and the full set of server-side and client-side [tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview). On the Claude API and Google Cloud, Claude Sonnet 5 also supports [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) as the stable `computer_toolset_20260801` toolset and the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) for tasks inside webpages, neither of which Claude Sonnet 4.6 supports; existing integrations on the earlier `computer_20251124` version continue to work unchanged on both models. To upgrade an existing integration, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models) is not available on Claude Sonnet 5. Claude Sonnet 5 also uses a new tokenizer.

2424

2525## Migrating to Claude Sonnet 5 from Claude Sonnet 4.6

2626

models/sonnet-5/whats-new-sonnet-5 Changed · +1 / -1 lines

from line 12

1212| --------------- | ----------------- | ---------------------------------------------- |

1313| Claude Sonnet 5 | `claude-sonnet-5` | The best combination of speed and intelligence |

1414

15Claude Sonnet 5 supports the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default (1M tokens is both the default and the maximum; there is no smaller context variant), 128k max output tokens, [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), and the same set of tools and platform features as Claude Sonnet 4.6, except [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models), which is not available on Claude Sonnet 5. On the Claude API, Claude Sonnet 5 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) and the stable `computer_toolset_20260801` version of the [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool), neither of which Claude Sonnet 4.6 supports; the earlier `computer_20251124` version is still accepted on both models. To upgrade an existing integration, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124).

15Claude Sonnet 5 supports the [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default (1M tokens is both the default and the maximum; there is no smaller context variant), 128k max output tokens, [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking), and the same set of tools and platform features as Claude Sonnet 4.6, except [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models), which is not available on Claude Sonnet 5. On the Claude API and Google Cloud, Claude Sonnet 5 also supports the [browser use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) and the stable `computer_toolset_20260801` version of the [computer use tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool), neither of which Claude Sonnet 4.6 supports; the earlier `computer_20251124` version is still accepted on both models. To upgrade an existing integration, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124).

1616

1717For complete pricing and specs, see the [models overview](https://platform.claude.com/docs/en/models/overview).

1818

release-notes/overview Changed · +2 / -1 lines

from line 15

1515### August 20, 2026

1616

1717* We've released **v1.0 of the [Python SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/sdks/python)**. The SDK's HTTP layer moves from `httpx` to [httpx2](https://httpx2.pydantic.dev), a maintained, API-compatible fork: build custom `http_client`, `Timeout`, and transport objects from `httpx2` (the `DefaultHttpxClient` helpers are unchanged), and call `httpx2.alias_httpx()` at startup if you rely on tracing or mocking libraries that patch `httpx`. v1.0 requires Python 3.10 or later and removes long-deprecated surface, including the legacy Text Completions API, the `temperature`, `top_p`, and `top_k` parameters on Messages methods, and the tool runner's client-side `compaction_control`. On the async client, `.with_raw_response` results now need `await response.parse()`, and `AnthropicBedrock` now raises an error when no AWS region is configured instead of defaulting to `us-east-1`. See the [v1 migration guide](https://github.com/anthropics/anthropic-sdk-python/blob/main/MIGRATION.md) for every change with before-and-after snippets.

18* The [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) and [browser use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool) toolsets (`computer_toolset_20260801` and `browser_toolset_20260801`) are now available on [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai) for Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, and Claude Opus 4.8. Requests use the same `tools` entries as on the Claude API.

1819

1920### August 19, 2026

2021

from line 31

3031

3132### August 18, 2026

3233

33* Workbench is now [**Playground**](https://platform.claude.com/playground) in the Claude Console. Playground supports every Messages API parameter and includes templates that demonstrate API features such as code execution and web search. It shows the full SDK request and the API response for each run, to help you understand the API and build with it. For more, see the [Claude Help Center](https://support.claude.com/en/articles/8606378-how-do-i-use-playground) or try it at [platform.claude.com/playground](https://platform.claude.com/playground).

34* Workbench is now [**playground**](https://platform.claude.com/playground) in the Claude Console. Playground supports every Messages API parameter and includes templates that demonstrate API features such as code execution and web search. It shows the full SDK request and the API response for each run, to help you understand the API and build with it. For more, see the [Claude Help Center](https://support.claude.com/en/articles/8606378-how-do-i-use-playground) or try it at [platform.claude.com/playground](https://platform.claude.com/playground).

3435

3536### August 11, 2026

3637

One read of Claude Developer Platformapi-20260826T150709Z

What this read moved

agents-and-tools/tool-use/browser-use-tool Changed · +3 / -3 lines

agents-and-tools/tool-use/computer-use-tool Changed · +3 / -3 lines

build-with-claude/claude-platform-on-aws Changed · +3 / -3 lines

build-with-claude/overview Changed · +7 / -7 lines

manage-claude/admin-api Changed · +4 / -4 lines

manage-claude/cmek Changed · +5 / -5 lines

manage-claude/compliance-content-data Changed · +21 / -12 lines

manage-claude/compliance-errors Changed · +17 / -7 lines

manage-claude/compliance-faq Changed · +4 / -4 lines

manage-claude/compliance-integration-patterns Changed · +6 / -3 lines

manage-claude/compliance-sessions Changed · +4 / -4 lines

manage-claude/usage-cost-api Changed · +7 / -3 lines

api/overview Changed · +1 / -1 lines

build-with-claude/claude-on-vertex-ai Changed · +1 / -2 lines

build-with-claude/prompt-engineering/prompting-claude-opus-4-8 Changed · +1 / -1 lines

build-with-claude/prompt-engineering/prompting-claude-sonnet-5 Changed · +1 / -1 lines

home Changed · +1 / -1 lines

intro Changed · +1 / -1 lines

manage-claude/api-and-data-retention Changed · +1 / -1 lines

manage-claude/cmek-aws-kms Changed · +1 / -1 lines

manage-claude/workspaces Changed · +1 / -1 lines

models/opus-5/migration-guide Changed · +2 / -2 lines

models/sonnet-5/migration-guide Changed · +1 / -1 lines

models/sonnet-5/whats-new-sonnet-5 Changed · +1 / -1 lines

release-notes/overview Changed · +2 / -1 lines