One read of Claude Developer Platformapi-20261026T223710Z
24 pages moved out of 821 read.
Pages moved
24
significant first
Pages read
821
in this capture
Captured
22:37 UTC
Corpus hash
8a6bb6037092
corpus-hash
What this read moved
1-24 of 24api/completions Changed · +3 / -13 lines
from line 247
247247
248248 The prompt that you want Claude to complete.
249249
250 For proper response generation you will need to format your prompt using alternating `
250 For proper response generation you will need to format your prompt using alternating `\n\nHuman:` and `\n\nAssistant:` conversational turns. For example:
251251
252 Human:`and`
253
254 Assistant:` conversational turns. For example:
255
256252 ```
257 "
258
259 Human: {userQuestion}
260
261 Assistant:"
253 "\n\nHuman: {userQuestion}\n\nAssistant:"
262254 ```
263255
264256 See [prompt validation](https://platform.claude.com/docs/en/build-with-claude/working-with-messages?sdk_languages=http) and our guide to [prompt design](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview?sdk_languages=http) for more details.
from line 273
281273
282274 Sequences that will cause the model to stop generating.
283275
284 Our models stop on `"
285
286 Human:"`, and may include additional built-in stop sequences in the future. By providing the stop_sequences parameter, you may include additional strings that will cause the model to stop generating.
276 Our models stop on `"\n\nHuman:"`, and may include additional built-in stop sequences in the future. By providing the stop_sequences parameter, you may include additional strings that will cause the model to stop generating.
287277
288278- `stream: optional boolean`
289279
api/completions/create Changed · +3 / -13 lines
from line 245
245245
246246 The prompt that you want Claude to complete.
247247
248 For proper response generation you will need to format your prompt using alternating `
248 For proper response generation you will need to format your prompt using alternating `\n\nHuman:` and `\n\nAssistant:` conversational turns. For example:
249249
250 Human:`and`
251
252 Assistant:` conversational turns. For example:
253
254250 ```
255 "
256
257 Human: {userQuestion}
258
259 Assistant:"
251 "\n\nHuman: {userQuestion}\n\nAssistant:"
260252 ```
261253
262254 See [prompt validation](https://platform.claude.com/docs/en/build-with-claude/working-with-messages?sdk_languages=http) and our guide to [prompt design](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview?sdk_languages=http) for more details.
from line 271
279271
280272 Sequences that will cause the model to stop generating.
281273
282 Our models stop on `"
283
284 Human:"`, and may include additional built-in stop sequences in the future. By providing the stop_sequences parameter, you may include additional strings that will cause the model to stop generating.
274 Our models stop on `"\n\nHuman:"`, and may include additional built-in stop sequences in the future. By providing the stop_sequences parameter, you may include additional strings that will cause the model to stop generating.
285275
286276- `stream: optional boolean`
287277
build-with-claude/claude-in-amazon-bedrock Changed · +5 / -11 lines
from line 350
350350
351351Use the latest version of Claude Code with Claude in Amazon Bedrock; run `claude update` to upgrade.
352352
353<Tip>
354 Upgrading to a newer Claude model? The [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model) in Claude Code applies model ID swaps and breaking parameter changes across your code base:
353Let Claude Code migrate your code to a newer model
355354
356 Let Claude Code migrate your code for you
357
358 ```text
359 /claude-api migrate this project to the latest Claude Opus model
360 ```
361
362 The skill detects which cloud platform your code targets and adjusts model ID formats and feature changes for that platform.
363</Tip>
355```text
356/claude-api migrate this project to the latest Claude Opus model
357```
364358
365359## Feature support
366360
build-with-claude/claude-in-microsoft-foundry Changed · +5 / -11 lines
from line 704
704704 [Claude Mythos Preview](https://anthropic.com/glasswing) is a research preview available to invited customers on Microsoft Foundry.
705705</Info>
706706
707<Tip>
708 Upgrading to a newer Claude model? The [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model) in Claude Code applies model ID swaps and breaking parameter changes across your code base:
707Let Claude Code migrate your code to a newer model
709708
710 Let Claude Code migrate your code for you
711
712 ```text
713 /claude-api migrate this project to the latest Claude Opus model
714 ```
715
716 The skill detects which cloud platform your code targets and adjusts model ID formats and feature changes for that platform.
717</Tip>
709```text
710/claude-api migrate this project to the latest Claude Opus model
711```
718712
719713## Billing
720714
build-with-claude/claude-models-on-google-cloud/google-managed Changed · +5 / -11 lines
from line 314
314314 Claude Mythos Preview is a research preview. Claude Models on Google Cloud (Google managed) offers it to invited customers. For more information, see [Project Glasswing](https://anthropic.com/glasswing).
315315</Note>
316316
317<Tip>
318 Upgrading to a newer Claude model? The [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model) in Claude Code applies model ID swaps and breaking parameter changes across your code base:
317Let Claude Code migrate your code to a newer model
319318
320 Let Claude Code migrate your code for you
321
322 ```text
323 /claude-api migrate this project to the latest Claude Opus model
324 ```
325
326 The skill detects which cloud platform your code targets and adjusts model ID formats and feature changes for that platform.
327</Tip>
319```text
320/claude-api migrate this project to the latest Claude Opus model
321```
328322
329323## Global, multi-region, and regional endpoints
330324
build-with-claude/claude-platform-on-aws Changed · +5 / -11 lines
from line 368
368368
369369New models typically launch on Claude Platform on AWS the same day as the first-party Claude API.
370370
371<Tip>
372 Upgrading to a newer Claude model? The [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model) in Claude Code applies model ID swaps and breaking parameter changes across your code base:
371Let Claude Code migrate your code to a newer model
373372
374 Let Claude Code migrate your code for you
375
376 ```text
377 /claude-api migrate this project to the latest Claude Opus model
378 ```
379
380 The skill detects which cloud platform your code targets and adjusts model ID formats and feature changes for that platform.
381</Tip>
373```text
374/claude-api migrate this project to the latest Claude Opus model
375```
382376
383377## Making requests
384378
build-with-claude/preserved-thinking Changed · +7 / -13 lines
from line 439
439439
440440### Check whether your code edits the prefix
441441
442<Tip>
443 **Automate this check with the Claude API skill.** In the latest version of [Claude Code](https://code.claude.com/docs/en/overview), open the repository that builds your requests and run the bundled [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#checking-an-integration-for-preserved-thinking):
442Let Claude Code check your code for you
444443
445 Let Claude Code check your code for you
444```text
445/claude-api preserved-thinking-migration
446```
446447
447 ```text
448 /claude-api preserved-thinking-migration
449 ```
450
451 The skill captures a few of your own multi-turn sessions and diffs consecutive requests to find where your code edits the prefix. It then replays the sessions with `"drop_block"` and counts the thinking blocks the API drops. After that, it fixes one cause at a time and measures again after each fix.
452</Tip>
453
454First, diff what you send. Capture the request bodies your integration sends over a few normal turns, including a compaction or a tool change. For each pair of consecutive requests, compare `system`, `tools`, and the `messages` they share. They should be identical up to the newly appended turns.
448To check by hand, first diff what you send. Capture the request bodies your integration sends over a few normal turns, including a compaction or a tool change. For each pair of consecutive requests, compare `system`, `tools`, and the `messages` they share. They should be identical up to the newly appended turns.
455449
456450Then confirm against the API. Add the `thinking-binding-controls-2026-08-01` beta header, set `prefix_mismatch_behavior` to `"drop_block"`, and run a normal multi-turn session through your integration on claude-fable-5-1. The following example runs two turns the way your integration should: `messages` only grows, each assistant turn goes back exactly as the API returned it, `thinking` blocks included, and `block_binding` is set on every request. After each turn it prints the number of `thinking` blocks in the response and the number of dropped blocks:
457451
manage-claude/claude-tag-api Changed · +26 / -24 lines
from line 479
479479
480480 ```java Java
481481 import com.anthropic.models.beta.organization.claudetag.BetaClaudeTagSettingsCreate;
482 import com.anthropic.models.beta.organization.claudetag.slackchannels.BetaClaudeTagSlackChannelIdentifiers;
482 import com.anthropic.models.beta.organization.claudetag.BetaClaudeTagSlackChannelIdentifiers;
483483 import com.anthropic.models.beta.organization.claudetag.slackchannels.SlackChannelCreateParams;
484484
485485 void main() {
from line 1497
14971497 new() { Settings = new() { GuestPolicy = new BetaClaudeTagGuestPolicyRestrict() } }
14981498 );
14991499
1500 Console.WriteLine(workspace.Settings.GuestPolicy?.Type.GetString());
1500 Console.WriteLine(workspace.Settings.GuestPolicy?.Type.Raw());
15011501 ```
15021502
15031503 ```go Go
from line 1850
18501850
18511851 await foreach (var target in page.Paginate())
18521852 {
1853 Console.WriteLine($"{target.ID}: {target.Type.GetString()}");
1853 Console.WriteLine($"{target.ID}: {target.Type.Raw()}");
18541854 }
18551855 ```
18561856
from line 1952
19521952 ```bash CLI
19531953 ant beta:organization:claude-tag:bundles:targets create \
19541954 --bundle-id capp_011CZkZjLP1cWxj5EtMmdgbq \
1955 --type slack_channel \
1956 --slack-channel-id slch_011CZkZmRt4vNq8sHbYw2KdX
1955 --target '{type: slack_channel, slack_channel_id: slch_011CZkZmRt4vNq8sHbYw2KdX}'
19571956 ```
19581957
19591958 ```python Python
from line 1960
19611960
19621961 target = client.beta.organization.claude_tag.bundles.targets.create(
19631962 "capp_011CZkZjLP1cWxj5EtMmdgbq",
1964 type="slack_channel",
1965 slack_channel_id="slch_011CZkZmRt4vNq8sHbYw2KdX",
1963 target={
1964 "type": "slack_channel",
1965 "slack_channel_id": "slch_011CZkZmRt4vNq8sHbYw2KdX",
1966 },
19661967 )
19671968
19681969 print(target.id)
from line 1974
19731974
19741975 const target = await client.beta.organization.claudeTag.bundles.targets.create(
19751976 "capp_011CZkZjLP1cWxj5EtMmdgbq",
1976 { type: "slack_channel", slack_channel_id: "slch_011CZkZmRt4vNq8sHbYw2KdX" }
1977 { target: { type: "slack_channel", slack_channel_id: "slch_011CZkZmRt4vNq8sHbYw2KdX" } }
19771978 );
19781979
19791980 console.log(target.id);
from line 1989
19881989 "capp_011CZkZjLP1cWxj5EtMmdgbq",
19891990 new()
19901991 {
1991 BetaClaudeTagBundleTargetCreate = new BetaClaudeTagSlackChannelBundleTargetCreate
1992 Target = new BetaClaudeTagSlackChannelBundleTargetCreate
19921993 {
19931994 SlackChannelID = "slch_011CZkZmRt4vNq8sHbYw2KdX",
19941995 },
from line 2006
20052006 context.Background(),
20062007 "capp_011CZkZjLP1cWxj5EtMmdgbq",
20072008 anthropic.BetaOrganizationClaudeTagBundleTargetNewParams{
2008 BetaClaudeTagBundleTargetCreate: anthropic.BetaClaudeTagBundleTargetCreateUnionParam{
2009 Target: anthropic.BetaClaudeTagBundleTargetCreateUnionParam{
20092010 OfSlackChannel: &anthropic.BetaClaudeTagSlackChannelBundleTargetCreateParam{
20102011 SlackChannelID: "slch_011CZkZmRt4vNq8sHbYw2KdX",
20112012 },
from line 2027
20262027 AnthropicClient client = AnthropicOkHttpClient.fromEnv();
20272028
20282029 var params = TargetCreateParams.builder()
2029 .slackChannelBetaClaudeTagBundleTargetCreate("slch_011CZkZmRt4vNq8sHbYw2KdX")
2030 .slackChannelTarget("slch_011CZkZmRt4vNq8sHbYw2KdX")
20302031 .build();
20312032 var target = client.beta().organization().claudeTag().bundles().targets()
20322033 .create("capp_011CZkZjLP1cWxj5EtMmdgbq", params);
from line 2041
20402041
20412042 $target = $client->beta->organization->claudeTag->bundles->targets->create(
20422043 bundleID: 'capp_011CZkZjLP1cWxj5EtMmdgbq',
2043 betaClaudeTagBundleTargetCreate: [
2044 target: [
20442045 'type' => 'slack_channel',
20452046 'slackChannelID' => 'slch_011CZkZmRt4vNq8sHbYw2KdX',
20462047 ],
from line 2056
20552056 bundle_id = "capp_011CZkZjLP1cWxj5EtMmdgbq"
20562057 target = client.beta.organization.claude_tag.bundles.targets.create(
20572058 bundle_id,
2058 beta_claude_tag_bundle_target_create: {
2059 target: {
20592060 type: :slack_channel,
20602061 slack_channel_id: "slch_011CZkZmRt4vNq8sHbYw2KdX"
20612062 }
from line 2093
20922093 ```bash CLI
20932094 ant beta:organization:claude-tag:bundles:targets create \
20942095 --bundle-id capp_011CZkZjLP1cWxj5EtMmdgbq \
2095 --type slack_workspace \
2096 --slack-workspace-id slws_011CZkZnWa7xPc3uJfZe5LgT
2096 --target '{type: slack_workspace, slack_workspace_id: slws_011CZkZnWa7xPc3uJfZe5LgT}'
20972097 ```
20982098
20992099 ```python Python
from line 2101
21012101
21022102 target = client.beta.organization.claude_tag.bundles.targets.create(
21032103 "capp_011CZkZjLP1cWxj5EtMmdgbq",
2104 type="slack_workspace",
2105 slack_workspace_id="slws_011CZkZnWa7xPc3uJfZe5LgT",
2104 target={
2105 "type": "slack_workspace",
2106 "slack_workspace_id": "slws_011CZkZnWa7xPc3uJfZe5LgT",
2107 },
21062108 )
21072109
21082110 print(target.id)
from line 2115
21132115
21142116 const target = await client.beta.organization.claudeTag.bundles.targets.create(
21152117 "capp_011CZkZjLP1cWxj5EtMmdgbq",
2116 { type: "slack_workspace", slack_workspace_id: "slws_011CZkZnWa7xPc3uJfZe5LgT" }
2118 { target: { type: "slack_workspace", slack_workspace_id: "slws_011CZkZnWa7xPc3uJfZe5LgT" } }
21172119 );
21182120
21192121 console.log(target.id);
from line 2130
21282130 "capp_011CZkZjLP1cWxj5EtMmdgbq",
21292131 new()
21302132 {
2131 BetaClaudeTagBundleTargetCreate = new BetaClaudeTagSlackWorkspaceBundleTargetCreate
2133 Target = new BetaClaudeTagSlackWorkspaceBundleTargetCreate
21322134 {
21332135 SlackWorkspaceID = "slws_011CZkZnWa7xPc3uJfZe5LgT",
21342136 },
from line 2147
21452147 context.Background(),
21462148 "capp_011CZkZjLP1cWxj5EtMmdgbq",
21472149 anthropic.BetaOrganizationClaudeTagBundleTargetNewParams{
2148 BetaClaudeTagBundleTargetCreate: anthropic.BetaClaudeTagBundleTargetCreateUnionParam{
2150 Target: anthropic.BetaClaudeTagBundleTargetCreateUnionParam{
21492151 OfSlackWorkspace: &anthropic.BetaClaudeTagSlackWorkspaceBundleTargetCreateParam{
21502152 SlackWorkspaceID: "slws_011CZkZnWa7xPc3uJfZe5LgT",
21512153 },
from line 2168
21662168 AnthropicClient client = AnthropicOkHttpClient.fromEnv();
21672169
21682170 var params = TargetCreateParams.builder()
2169 .slackWorkspaceBetaClaudeTagBundleTargetCreate("slws_011CZkZnWa7xPc3uJfZe5LgT")
2171 .slackWorkspaceTarget("slws_011CZkZnWa7xPc3uJfZe5LgT")
21702172 .build();
21712173 var target = client.beta().organization().claudeTag().bundles().targets()
21722174 .create("capp_011CZkZjLP1cWxj5EtMmdgbq", params);
from line 2182
21802182
21812183 $target = $client->beta->organization->claudeTag->bundles->targets->create(
21822184 bundleID: 'capp_011CZkZjLP1cWxj5EtMmdgbq',
2183 betaClaudeTagBundleTargetCreate: [
2185 target: [
21842186 'type' => 'slack_workspace',
21852187 'slackWorkspaceID' => 'slws_011CZkZnWa7xPc3uJfZe5LgT',
21862188 ],
from line 2197
21952197 bundle_id = "capp_011CZkZjLP1cWxj5EtMmdgbq"
21962198 target = client.beta.organization.claude_tag.bundles.targets.create(
21972199 bundle_id,
2198 beta_claude_tag_bundle_target_create: {
2200 target: {
21992201 type: :slack_workspace,
22002202 slack_workspace_id: "slws_011CZkZnWa7xPc3uJfZe5LgT"
22012203 }
from line 2257
22552257 new() { BundleID = "capp_011CZkZjLP1cWxj5EtMmdgbq" }
22562258 );
22572259
2258 Console.WriteLine(target.Type.GetString());
2260 Console.WriteLine(target.Type.Raw());
22592261 ```
22602262
22612263 ```go Go
manage-claude/compliance-faq Changed · +4 / -4 lines
from line 16
1616 </Accordion>
1717
1818 <Accordion title="Can I turn the Compliance API off after enabling it in Claude Console?">
19 Yes. For a standalone Claude Console organization, an organization admin can turn the **Compliance API** toggle off on the [Compliance](https://platform.claude.com/settings/security) page (`platform.claude.com/settings/security`) in the Claude Console, the same place it is turned on. While the Compliance API is off, no activity events are recorded for your organization, so the [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed) receives no new events. If your organization is enrolled in [Access Transparency](https://platform.claude.com/docs/en/manage-claude/access-transparency), turning the Compliance API off also stops Access Transparency event delivery. Activity that is not recorded while the Compliance API is off cannot be recovered later. Turning the Compliance API back on resumes recording from that point forward; activity that was already recorded is not deleted.
19 Yes. For a standalone Claude Console organization, an organization admin can turn the **Compliance API** toggle off on the [Compliance](https://platform.claude.com/settings/security) page (`platform.claude.com/settings/security`) in the Claude Console, the same place it is turned on. While the Compliance API is off, no activity events are recorded for your organization, so the [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed) receives no new events. Activity that is not recorded while the Compliance API is off cannot be recovered later. Turning the Compliance API back on resumes recording from that point forward; activity that was already recorded is not deleted. Access Transparency events are an exception. If your organization is enrolled in [Access Transparency](https://platform.claude.com/docs/en/manage-claude/access-transparency), turning the Compliance API off stops your access to these events, not their recording. They are still recorded while the Compliance API is off, and the Activity Feed returns them after the Compliance API is turned back on.
2020 </Accordion>
2121
2222 <Accordion title="Does turning the Compliance API off delete events that were already captured?">
23 No. Turning the Compliance API off stops new activity events from being recorded, but it does not delete events that were already captured while it was on. Recording resumes from the point the Compliance API is turned back on.
23 No. Turning the Compliance API off stops new activity events from being recorded, but it does not delete events that were already captured while it was on. Recording resumes from the point the Compliance API is turned back on. Access Transparency events are an exception: they are still recorded while the Compliance API is off.
2424 </Accordion>
2525
2626 <Accordion title="Is turning the Compliance API off in Claude Console recorded anywhere?">
27 Yes. When the Compliance API is turned off (or back on) in Claude Console, the change is recorded as an `org_compliance_api_settings_updated` activity in the [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed), so your audit trail shows who changed the setting and when. This activity is an exception to the recording stop: the disable is recorded even though no other activity is recorded while the Compliance API is off.
27 Yes. When the Compliance API is turned off (or back on) in Claude Console, the change is recorded as an `org_compliance_api_settings_updated` activity in the [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed), so your audit trail shows who changed the setting and when. This activity is an exception: the disable is recorded even though other activity is not recorded while the Compliance API is off. Access Transparency events are also an exception.
2828 </Accordion>
2929
3030 <Accordion title="Why doesn't my parent organization appear in Claude Console when creating an Admin API key?">
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), unless a user deletes it sooner.
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. Access Transparency events are an exception. If your organization is enrolled in [Access Transparency](https://platform.claude.com/docs/en/manage-claude/access-transparency), these events are recorded even while the Compliance API is off. The feed can therefore include some from before the Compliance API was first enabled. 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?">
manage-claude/opentelemetry Changed · +6 / -0 lines
from line 13
1313 OpenTelemetry export is in beta. It's provided under your agreement with Anthropic, including the Beta Services section of the [Service Specific Terms](https://www.anthropic.com/legal/service-specific-terms).
1414</Note>
1515
16<video aria-label="Trace agents with OpenTelemetry on the Claude Platform">
17 <source src="https://media.platform.claude.com/docs/opentelemetry/tracing/overview-1080p.mp4" type="video/mp4" media="(min-width: 1280px)" />
18 <source src="https://media.platform.claude.com/docs/opentelemetry/tracing/overview-720p.mp4" type="video/mp4" media="(min-width: 640px)" />
19 <source src="https://media.platform.claude.com/docs/opentelemetry/tracing/overview-480p.mp4" type="video/mp4" />
20</video>
21
1622The Claude API and the SDK can trace your Messages API requests, tool uses, and Managed Agents sessions with [OpenTelemetry](https://opentelemetry.io/) (OTel). You can view these traces in the observability platform you already have. Use them to debug failed or slow requests, track token spend and latency, and build evals from real traffic. You can also see each request inside your application's own traces, linked to the user or feature that sent it.
1723
1824OpenTelemetry is a vendor-neutral standard that most observability platforms support. A *trace* is the full record of one request through your system. A *span* is one step in a trace, such as a model request or a tool use. The API and the SDK use attributes from the [GenAI semantic conventions](https://github.com/open-telemetry/semantic-conventions-genai), so platforms that support the conventions can recognize the spans without extra setup.
managed-agents/quickstart Changed · +5 / -9 lines
from line 12
1212
1313This guide walks you through creating an agent, setting up an environment, starting a session, and streaming agent responses.
1414
15<Tip>
16 **Prefer an interactive walkthrough?** The latest version of [Claude Code](https://claude.com/product/claude-code) can guide you through the setup and answer your questions:
15Let Claude Code set up your agent for you
1716
18 Let Claude Code set up your agent for you
19
20 ```text
21 /claude-api managed-agents-onboard
22 ```
23</Tip>
17```text
18/claude-api managed-agents-onboard
19```
2420
2521## Core concepts
2622
models/fable-5-1/migration-guide Changed · +5 / -11 lines
from line 8
88 This guide covers migrating [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) code. If you use [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), no changes beyond updating the model name are required.
99</Note>
1010
11<Tip>
12 **Automate your migration with the [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model).** It comes bundled with Claude Code and works for any current Claude model as the target:
11Let Claude Code migrate your code for you
1312
14 Let Claude Code migrate your code for you
15
16 ```text
17 /claude-api migrate this project to claude-fable-5-1
18 ```
19
20 The skill applies the model ID swap and, as needed, breaking parameter changes, prefill replacement, and effort calibration for your target model across your code base, then produces a checklist of items to verify manually. It asks you to confirm the migration scope (entire working directory, a subdirectory, or a specific file list) before editing any files. The skill also detects Amazon Bedrock and Claude Platform on AWS clients and adjusts model ID formats and feature changes for those platforms.
21</Tip>
13```text
14/claude-api migrate this project to claude-fable-5-1
15```
2216
2317[Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1) succeeds Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost. It's available on the Claude API, [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), and [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry). [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview) shares the same capabilities and is available only to organizations verified through Anthropic's verification programs, such as the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). For behavioral differences and prompting patterns, see [Prompting Claude Fable 5.1](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1).
2418
models/haiku-5-5/migration-guide Changed · +4 / -10 lines
from line 8
88 This guide covers migrating [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) code. If you use [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), no changes beyond updating the model name are required.
99</Note>
1010
11<Tip>
12 **Automate your migration with the [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model).** It comes bundled with Claude Code and works for any current Claude model as the target:
11Let Claude Code migrate your code for you
1312
14 Let Claude Code migrate your code for you
15
16 ```text
17 /claude-api migrate this project to claude-haiku-5-5
18 ```
19
20 The skill applies the model ID swap and, as needed, breaking parameter changes, prefill replacement, and effort calibration for your target model across your code base, then produces a checklist of items to verify manually. It asks you to confirm the migration scope (entire working directory, a subdirectory, or a specific file list) before editing any files. The skill also detects Amazon Bedrock and Claude Platform on AWS clients and adjusts model ID formats and feature changes for those platforms.
21</Tip>
13```text
14/claude-api migrate this project to claude-haiku-5-5
15```
2216
2317This guide covers moving code that calls Claude Haiku 4.5 to Claude Haiku 5.5. For code that calls Claude Haiku 3.5 or Claude Haiku 3, also make the changes in [Migrating to Claude Haiku 5.5 from Claude Haiku 3.5 and earlier Haiku models](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#migrating-from-haiku-35). To move up to a Sonnet or Opus model instead, see [Upgrade between model versions](https://platform.claude.com/docs/en/about-claude/models/migration-guide). For how long Claude Haiku 4.5 stays available, see [Model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations).
2418
models/opus-5-5/migration-guide Changed · +5 / -11 lines
from line 8
88 This guide covers migrating [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) code. If you use [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), no changes beyond updating the model name are required.
99</Note>
1010
11<Tip>
12 **Automate your migration with the [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model).** It comes bundled with Claude Code and works for any current Claude model as the target:
11Let Claude Code migrate your code for you
1312
14 Let Claude Code migrate your code for you
15
16 ```text
17 /claude-api migrate this project to claude-opus-5-5
18 ```
19
20 The skill applies the model ID swap and, as needed, breaking parameter changes, prefill replacement, and effort calibration for your target model across your code base, then produces a checklist of items to verify manually. It asks you to confirm the migration scope (entire working directory, a subdirectory, or a specific file list) before editing any files. The skill also detects Amazon Bedrock and Claude Platform on AWS clients and adjusts model ID formats and feature changes for those platforms.
21</Tip>
13```text
14/claude-api migrate this project to claude-opus-5-5
15```
2216
2317This page lists the code changes for moving to Claude Opus 5.5 from [Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-5), [Claude Opus 4.8](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-4-8), [Claude Opus 4.7](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-47), [Claude Opus 4.6 and earlier Opus models](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-opus-46), or [Claude Sonnet 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migrating-from-claude-sonnet-5). Every reader needs [What every request to Claude Opus 5.5 must satisfy](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#request-requirements) and [Handle thinking in every response](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-in-every-response). Then go to the section for your current model: its first sentence names the other sections that apply to you. The [migration checklist](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#migration-checklist) lists every change by starting model.
2418
models/sonnet-5-5/migration-guide Changed · +5 / -11 lines
from line 10
1010 This guide covers migrating [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) code. If you use [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), no changes beyond updating the model name are required.
1111</Note>
1212
13<Tip>
14 **Automate your migration with the [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model).** It comes bundled with Claude Code and works for any current Claude model as the target:
13Let Claude Code migrate your code for you
1514
16 Let Claude Code migrate your code for you
17
18 ```text
19 /claude-api migrate this project to claude-sonnet-5-5
20 ```
21
22 The skill applies the model ID swap and, as needed, breaking parameter changes, prefill replacement, and effort calibration for your target model across your code base, then produces a checklist of items to verify manually. It asks you to confirm the migration scope (entire working directory, a subdirectory, or a specific file list) before editing any files. The skill also detects Amazon Bedrock and Claude Platform on AWS clients and adjusts model ID formats and feature changes for those platforms.
23</Tip>
15```text
16/claude-api migrate this project to claude-sonnet-5-5
17```
2418
2519Claude Sonnet 5.5 has the same prices as Claude Sonnet 5, except for prompt cache reads, which cost $0.10 USD per million tokens, half the Claude Sonnet 5 rate. See [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing). For its context window and output limits, see the [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) model page. For features and prompting, see [What's new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#feature-support) and [Prompting Claude Sonnet 5.5](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5).
2620
release-notes/overview Changed · +4 / -4 lines
### October 23, 2026
from line 12
1212 For updates to Claude Code, see the [complete CHANGELOG.md](https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md) in the `claude-code` repository.
1313</Tip>
1414
15### October 23, 2026
16
17* The [Claude Tag API](https://platform.claude.com/docs/en/manage-claude/claude-tag-api) is available in beta for Claude Enterprise organizations with the `experimental-claude-tag-2026-10-21` beta header. Its `/v1/organizations/claude_tag/` endpoints read and change [Claude Tag](https://claude.com/docs/claude-tag/overview) settings on Slack channels and Slack workspaces, show which settings apply in a channel and where each comes from, and attach Access bundles. Call it with an Admin API key that your primary owner creates in claude.ai with the `read:claude_tag` or `write:claude_tag` scope. It is not available to Claude Platform (Claude Console) organizations.
18
1519### October 22, 2026
1620
1721* We've launched [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), the Claude API operated by Anthropic and reached through your Google Cloud project. Google Cloud IAM controls access. Google Cloud Marketplace handles billing.
from line 27
2327* We've released new versions of the [client SDKs](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) and the [`ant` CLI](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/quickstart) that send API version `2026-10-21` by default: Python SDK 2.0.0, TypeScript SDK 1.0.0, C# SDK 13.0.0, Go SDK 2.0.0, Java SDK 3.0.0, PHP SDK 1.0.0, Ruby SDK 2.0.0, and `ant` CLI 2.0.0. See [Switch to 2026-10-21](https://platform.claude.com/docs/en/api/migration-2026-10-21#upgrade).
2428* The new SDK and CLI versions also have breaking changes that don't depend on the API version, and they are licensed under Apache 2.0 instead of the MIT License. See [SDK and CLI changes](https://platform.claude.com/docs/en/api/migration-2026-10-21#sdk-changes).
2529* We've added the `enforcement_status` and `enforcement_actions` fields to [user profiles](https://platform.claude.com/docs/en/manage-claude/user-profiles), so you can see whether Anthropic has restricted or banned one of your end customers. To find the profiles that have an open restriction or ban, [list your profiles](https://platform.claude.com/docs/en/api/user_profiles/list) with the new `enforcement_status[]` filter. See [Check whether Anthropic has restricted or banned a profile](https://platform.claude.com/docs/en/manage-claude/user-profiles#check-whether-anthropic-has-restricted-or-banned-a-profile).
26
27### October 20, 2026
28
29* The [Claude Tag API](https://platform.claude.com/docs/en/manage-claude/claude-tag-api) is available in beta for Claude Enterprise organizations with the `experimental-claude-tag-2026-10-21` beta header. Its `/v1/organizations/claude_tag/` endpoints read and change [Claude Tag](https://claude.com/docs/claude-tag/overview) settings on Slack channels and Slack workspaces, show which settings apply in a channel and where each comes from, and attach Access bundles. Call it with an Admin API key that your primary owner creates in claude.ai with the `read:claude_tag` or `write:claude_tag` scope. It is not available to Claude Platform (Claude Console) organizations.
3030
3131### October 20, 2026
3232
about-claude/models/optimizing-for-cost-and-intelligence Changed · +2 / -2 lines
from line 196
196196 
197197</Frame>
198198
199The stakes are highest on Claude Fable 5.1 and Claude Mythos 5.1, where a break re-writes the prefix at 1.25x the input price instead of reading it at 0.025x. On Claude Haiku 5.5 a system prompt edit costs 12.5 times an unchanged request. The edit re-wrote the whole conversation. By default, newer accounts get a 400 error instead[18](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs). The top-level effort change, in a conversation that held the model's first reply with its thinking, re-wrote all but the system prompt. These figures are from the Messages API.
199At list prices, the stakes are highest on Claude Fable 5.1 and Claude Mythos 5.1, where a break re-writes the prefix at 1.25x the input price instead of reading it at 0.025x. On Claude Haiku 5.5 a system prompt edit costs 12.5 times an unchanged request. The edit re-wrote the whole conversation. By default, newer accounts get a 400 error instead, except on Claude Mythos 5.1[18](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs). The top-level effort change, in a conversation that held the model's first reply with its thinking, re-wrote all but the system prompt. These figures are from the Messages API.
200200
201201**What to do.**
202202
from line 1033
1033103318. **Cache-break, compaction timing, and status-line measurements:**
10341034
10351035 * **October 2026 test, one change to a long conversation:** Measured October 20, 2026, on Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5, on the Messages API with no tools, adaptive thinking, each model's default effort, the 5-minute cache, a cache breakpoint on the system prompt, and [automatic caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#automatic-caching). The conversation held about 101,000 tokens: a 20,000-token system prompt, 13 user turns of filler text, the model's own reply to the first turn with its thinking block, and one-word replies to the rest. Once one request had cached the conversation, a second added one short turn, and each measured request sent that longer conversation with one change. Two conversations per model gave the same result.
1036 * **October 2026 test, tokens read and written:** With no change, and with a per-message effort change, the request read all 101,000 tokens and wrote none. With a 25-token mid-conversation system message, or a 25-token status line at the end of the newest user turn, it read them all and wrote only the new text. A top-level effort change (to `low` on Claude Fable 5.1 and Claude Sonnet 5.5, to `high` on Claude Opus 5.5 and Claude Haiku 5.5) read the 20,000-token system prompt and wrote 81,000 tokens. The same 25 tokens at the front or the end of the system prompt read nothing and wrote all 101,000. The request after a mid-conversation system message, a top-level effort change, or 25 tokens added to the end of the system prompt read the new prefix; a new status line at the front wrote everything again. A further test on October 21, 2026, on the same four models with conversations of 5,000 or 100,000 tokens and one-word replies, sent a beta header for the first time mid-conversation, as a first per-message effort change may: that request read everything the request before it had cached, all 54 times. A system message sent with no beta header did the same, all 15 times.
1036 * **October 2026 test, tokens read and written:** With no change, and with a per-message effort change, the request read all 101,000 tokens and wrote none. With a 25-token mid-conversation system message, or a 25-token status line at the end of the newest user turn, it read them all and wrote only the new text. A top-level effort change (to `low` on Claude Fable 5.1 and Claude Sonnet 5.5, to `high` on Claude Opus 5.5 and Claude Haiku 5.5) read the 20,000-token system prompt and wrote 81,000 tokens. The same 25 tokens at the front or the end of the system prompt read nothing and wrote all 101,000. The request after a mid-conversation system message, a top-level effort change, or 25 tokens added to the end of the system prompt read the new prefix; a new status line at the front wrote everything again. A further test on October 21, 2026, on the same four models with conversations of 5,000 tokens, and on all but Claude Fable 5.1 with conversations of 100,000 tokens, all with one-word replies, sent a beta header for the first time mid-conversation, as a first per-message effort change may: that request read everything the request before it had cached, all 54 times. A system message sent with no beta header did the same, all 15 times.
10371037 * **October 2026 test, how priced:** The chart gives the prompt side of one request, from its `usage` fields at list prices. The chart's values, in the order system prompt edit, system message, top-level effort change, and per-message effort change: Claude Fable 5.1 $1.26 USD, $0.026 USD, $1.02 USD, and $0.025 USD; Claude Opus 5.5 $0.50 USD, $0.020 USD, $0.41 USD, and $0.020 USD; Claude Sonnet 5.5 $0.25 USD, $0.010 USD, $0.20 USD, and $0.010 USD. The unchanged request repeated an earlier request byte for byte; a new turn of about 25 tokens adds under $0.001 USD. On Claude Haiku 5.5, whose requests were over 100,000 prompt tokens and so at its [long context prices](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing): $0.063 USD for the system prompt edit, $0.052 USD for the effort change, and $0.005 USD for the read. The requests ran on an Anthropic-internal organization whose usage is metered the same way as a customer organization's, and on which the API does not enforce the [prefix check](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check) by default, so its system prompt edits were accepted. On accounts created on or after August 31, 2026, 00:00 UTC, a request to one of these four models that sends earlier thinking blocks back gets a 400 error by default if it changes `system`, `tools`, or a message before one of them.
10381038 * **What was measured:** The triage agent's long variant from [Trim input and context tokens](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#trim-input-and-context-tokens), run August 24, 2026, on Claude Sonnet 5 with the 5-minute cache, cost from the usage fields at list prices, five sessions per arm: a no-change arm at the default effort throughout ($0.81 USD per session), and two arms that start at low effort and make the same two cache-breaking changes, a switch to the default effort and one added tool, either mid-session at requests 12 and 17 ($0.95 USD) or together on the first request after the first compaction ($0.75 USD).
10391039 * **Fourth arm:** A fourth arm of six sessions, run August 25, 2026, made the same two changes on the request that triggered the first compaction ($0.92 USD per session): that request's summarization pass wrote the 81,000-token context to the cache instead of reading it, so that pass cost $0.21 USD against $0.04 USD for the same pass in the boundary arm.
cli-sdks-libraries/cli/using Changed · +1 / -1 lines
from line 117
117117 --name "Research Agent" \
118118 --model '{id: claude-opus-5-5}' \
119119 --tool '{type: agent_toolset_20260401}' \
120 --tool '{type: custom, name: search_docs, input_schema: {type: object, properties: {query: {type: string}}}}'
120 --tool '{type: custom, name: search_docs, description: Search the documentation, input_schema: {type: object, properties: {query: {type: string}}}}'
121121```
122122
123123### Stdin
manage-claude/access-transparency Changed · +2 / -0 lines
from line 74
7474
7575Pagination, date-range filtering (`created_at.gte` / `.lt`), and the response envelope (`has_more`, `first_id`, `last_id`) are shared with the rest of the Activity Feed. See [Query the Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed).
7676
77Turning the Compliance API off stops your access to Access Transparency events, not their recording. The Activity Feed returns them after the Compliance API is turned back on.
78
7779Each `anthropic_access` activity carries the standard Activity fields plus the following:
7880
7981| Field | Type | Description |
manage-claude/analytics-api Changed · +1 / -1 lines
from line 144
144144* **Code changes:** In user activity, these fields in `claude_code_metrics.core_metrics` can be zero: `lines_of_code` (lines added and removed) and `commit_count`. The `pull_request_count` field can be lower than the real number of pull requests.
145145* **Skills started with a slash command:** If a user starts a skill in Claude Code or Cowork by typing a slash command, such as `/skill-name`, that use is not counted. This applies to skill usage, and to Cowork skill counts in user activity. Skills that Claude invokes without a slash command are still counted.
146146
147For other analytics changes with customer-managed encryption keys, see [Customer-managed encryption keys](https://platform.claude.com/docs/en/manage-claude/cmek#disabled-or-modified).
147For other analytics changes with customer-managed encryption keys, see [What CMEK covers on Claude Enterprise](https://platform.claude.com/docs/en/manage-claude/cmek-coverage-claude-enterprise#turned-off-or-changed).
148148
149149## Next steps
150150
manage-claude/api-and-data-retention Changed · +2 / -1 lines
from line 56
5656### What HIPAA readiness covers
5757
5858* **Claude API:** HIPAA readiness applies to the Claude API (`api.anthropic.com`) for eligible features listed in the [feature eligibility table](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility).
59* **Claude in Microsoft Foundry:** [Claude in Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) (Hosted on Anthropic or Hosted on Azure) is an eligible service for customers with a BAA with Anthropic plus the HIPAA configuration enabled on the Azure subscription. Request the HIPAA configuration through your Anthropic account team. For requirements and covered features, see the [HIPAA Implementation Guide](https://trust.anthropic.com/resources).
5960
6061### What HIPAA readiness does not cover
6162
from line 63
6263* **Claude consumer products:** Claude Free, Pro, and Max plans.
6364* **Claude Console:** Usage through the Claude Console interface (enabling HIPAA readiness from Console settings is supported; processing PHI through the Console is not covered).
6465* **Partner-operated platforms:** Amazon Bedrock and Google Cloud's Agent Platform. Refer to those platforms' compliance documentation.
65* **Claude Platform on AWS and Microsoft Foundry:** HIPAA readiness is not available on these platforms.
66* **Claude Platform on AWS:** HIPAA readiness is not available on Claude Platform on AWS.
6667* **Third-party integrations:** Data processed by external tools or services connected to your application.
6768* **Claude Code:** Claude Code is not covered under HIPAA readiness.
6869* **Beta features:** Features in beta are generally not covered under the BAA unless explicitly listed as eligible in the [feature eligibility table](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#feature-eligibility).
manage-claude/compliance-activity-feed Changed · +1 / -1 lines
from line 14
1414 Both Compliance Access Keys (`sk-ant-api01-...`) carrying this scope and Admin API keys (`sk-ant-admin01-...`) can call the Activity Feed. See [Set up the Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api-access) for the conditions under which each key type carries the scope.
1515</Check>
1616
17The Activity Feed records authentication, chat, file, project, administrative, and platform activity across your organization and returns it in reverse chronological order. Activities are queryable within 1 minute of occurring and are retained for 6 years. Recording is not retroactive: it begins when the Compliance API is first enabled for your organization, and activity from before enablement is not backfilled.
17The Activity Feed records authentication, chat, file, project, administrative, and platform activity across your organization and returns it in reverse chronological order. Activities are queryable within 1 minute of occurring and are retained for 6 years. Recording is not retroactive: it begins when the Compliance API is first enabled for your organization, and activity from before enablement is not backfilled. Access Transparency events are an exception. If your organization is enrolled in [Access Transparency](https://platform.claude.com/docs/en/manage-claude/access-transparency), these events are recorded even while the Compliance API is off. The feed can therefore include some from before the Compliance API was first enabled.
1818
1919```bash cURL
2020curl --fail-with-body -sS \
manage-claude/compliance-api-access Changed · +1 / -1 lines
from line 46
4646 * **Claude Console organizations linked to a parent organization:** There is nothing to turn on in Claude Console. Ask the primary owner of your parent organization to enable the Compliance API in claude.ai, or contact your account team.
4747
4848 <Warning>
49 **Turning the Compliance API off stops activity recording.** An organization admin can turn the Compliance API off at any time with the same **Compliance API** toggle that turns it on. While the Compliance API is off, no activity events are recorded for your organization, so the [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed) receives no new events. If your organization is enrolled in [Access Transparency](https://platform.claude.com/docs/en/manage-claude/access-transparency), turning the Compliance API off also stops Access Transparency event delivery. Activity that is not recorded while the Compliance API is off cannot be recovered later. Turning the Compliance API back on resumes recording from that point forward; activity that was already recorded is not deleted. For Claude Enterprise organizations, the Compliance API setting in claude.ai also governs transcript capture for [local sessions](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions) (sessions on users' machines): capture starts when the Compliance API is enabled and stops while it is off, and transcript content from sessions that run while it is off is not captured and cannot be recovered later.
49 **Turning the Compliance API off stops activity recording.** An organization admin can turn the Compliance API off at any time with the same **Compliance API** toggle that turns it on. While the Compliance API is off, no activity events are recorded for your organization, so the [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed) receives no new events. Activity that is not recorded while the Compliance API is off cannot be recovered later. Turning the Compliance API back on resumes recording from that point forward; activity that was already recorded is not deleted. Access Transparency events are an exception. If your organization is enrolled in [Access Transparency](https://platform.claude.com/docs/en/manage-claude/access-transparency), turning the Compliance API off stops your access to these events, not their recording. They are still recorded while the Compliance API is off, and the Activity Feed returns them after the Compliance API is turned back on. For Claude Enterprise organizations, the Compliance API setting in claude.ai also governs transcript capture for [local sessions](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions) (sessions on users' machines): capture starts when the Compliance API is enabled and stops while it is off, and transcript content from sessions that run while it is off is not captured and cannot be recovered later.
5050 </Warning>
5151
5252 A standalone Claude Console organization uses Admin API keys rather than Compliance Access Keys: after enablement, skip the remaining steps and [create a new Admin API key](https://platform.claude.com/docs/en/manage-claude/compliance-api-access#create-an-admin-api-key) instead. The remaining steps provision Compliance Access Keys, which are available only to organizations that are part of a Claude Enterprise tenant.
manage-claude/compliance-integration-patterns Changed · +1 / -1 lines
from line 26
2626
2727Both patterns share these constraints:
2828
29* Activities are queryable within 1 minute of occurring and retained for 6 years. Recording is not retroactive: it begins when the Compliance API is first enabled for your organization, and activity from before enablement is not backfilled.
29* Activities are queryable within 1 minute of occurring and retained for 6 years. Recording is not retroactive: it begins when the Compliance API is first enabled for your organization, and activity from before enablement is not backfilled. Access Transparency events are an exception. If your organization is enrolled in [Access Transparency](https://platform.claude.com/docs/en/manage-claude/access-transparency), these events are recorded even while the Compliance API is off. The feed can therefore include some from before the Compliance API was first enabled.
3030* The maximum `limit` for each page is 5,000.
3131* Cursor values are opaque strings that you must not parse.
3232* Requests are limited to 600 per minute for each [parent organization](https://platform.claude.com/docs/en/manage-claude/compliance-api#how-the-compliance-api-works), shared across every key, every linked organization, and every `/v1/compliance/*` endpoint; unlike the local session endpoints, the remote session endpoints carry a second request budget on top. See [429 Too Many Requests](https://platform.claude.com/docs/en/manage-claude/compliance-errors#429-too-many-requests) for the response headers and retry contract.