Claude Developer Platform documentation
812 pages as of the newest read. Every one links to its own history: what it said before, and what changed when.
Pages tracked812in the newest capture
Last read23 Oct 202600:07 UTC
Removed upstream164pages gone since this site started reading
Captures kept155reads this site has made of this source
This captureapiapi-20261023T000722Z
The newest read
15 pages changed on 23 Oct 2026
/
15 rows
ReadPageWhatLines
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
±changed
+3−2
apichanged
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
function resetConversation(&$messages) {
function resetConversation(&$messages)
{
echo "Error: " . $e->getMessage() . "\n";
echo 'Error: ' . $e->getMessage() . "\n";
+3 −2 lines
Recorded here 23 Oct 2026 00:07 UTC
test-and-evaluate/develop-tests
±changed
+27−27
apichanged
test-and-evaluate/develop-tests
// is simplified to whitespace words; scores may differ from the Python rouge library.
// is simplified to whitespace words; scores might differ from the Python rouge library.
// is simplified to whitespace words; scores may differ from the Python rouge library.
// is simplified to whitespace words; scores might differ from the Python rouge library.
// is simplified to whitespace words; scores may differ from the Python rouge library.
+27 −27 lines
Recorded here 23 Oct 2026 00:07 UTC
models/sonnet-5-5/whats-new-sonnet-5-5
±changed
+8−8
apichanged
models/sonnet-5-5/whats-new-sonnet-5-5
* [On the Claude API and Claude Models on Google Cloud (Google managed), the earlier `computer_20251124` computer use tool is not accepted](https://platform.claude.com/docs/en/mode
* [The advisor tool rejects Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5, and Claude Haiku 5.5 as advisors](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-son
* On the Claude API and Claude Models on Google Cloud (Google managed), [the earlier `computer_20251124` computer use tool is not accepted](https://platform.claude.com/docs/en/mode
* [The advisor tool rejects four models as advisors](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#advisor-tool-pairings): Claude Opus 4.8, Claude Opus
Claude Sonnet 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), [mid-conversation system m
+8 −8 lines
Recorded here 23 Oct 2026 00:07 UTC
models/sonnet-5-5/overview
±changed
+2−2
apichanged
models/sonnet-5-5/overview
* [On the Claude API and Claude Models on Google Cloud (Google managed), the earlier `computer_20251124` computer use tool is not accepted](https://platform.claude.com/docs/en/mode
* [The advisor tool rejects Claude Opus 4.8, Claude Opus 4.7, Claude Sonnet 5, and Claude Haiku 5.5 as advisors](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-son
* On the Claude API and Claude Models on Google Cloud (Google managed), [the earlier `computer_20251124` computer use tool is not accepted](https://platform.claude.com/docs/en/mode
* [The advisor tool rejects four models as advisors](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5#advisor-tool-pairings): Claude Opus 4.8, Claude Opus
+2 −2 lines
Recorded here 23 Oct 2026 00:07 UTC
models/sonnet-5-5/migration-guide
±changed
+8−5
apichanged
models/sonnet-5-5/migration-guide
This request works on Claude Sonnet 5.5 as written. The example sets an effort level and, in the SDK, reads the reply by block type. It leaves out five settings that return a 400 e
This request works on Claude Sonnet 5.5 as written. It sets an effort level, and the SDK example reads the reply by block type. It leaves out five settings that return a 400 error:
new UserMessageParam {
new UserMessageParam
{
+8 −5 lines
Recorded here 23 Oct 2026 00:07 UTC
models/overview
±changed
+21−21
apichanged
models/overview
| Feature | Claude Fable 5.1
| :-------------------------------------------------------------------------------------------------------- | :---------------------------------------------------------------------
| Description | For demanding reasoning and long-horizon agentic work
| Model page | [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-
| Comparative latency | Slower
+21 −21 lines
Recorded here 23 Oct 2026 00:07 UTC
models/opus-5-5/whats-new-opus-5-5
±changed
+5−5
apichanged
models/opus-5-5/whats-new-opus-5-5
Claude Opus 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), [mid-conversation system mes
Claude Opus 5.5 supports [per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) (beta), [mid-conversation system mes
* **Claude API:** all customers, as `claude-opus-5-5`.
* **AWS:** [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), as `anthropic.claude-opus-5-5`, and [Claude Platform on AWS](
* **Google Cloud:** [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), as `
+5 −5 lines
Recorded here 23 Oct 2026 00:07 UTC
models/opus-5-5/migration-guide
±changed
+10−7
apichanged
models/opus-5-5/migration-guide
new UserMessageParam {
new UserMessageParam
{
.map(customTool -> customTool.toBuilder().strict(true).build())
.map(customTool -> customTool.toBuilder()
+10 −7 lines
Recorded here 23 Oct 2026 00:07 UTC
models/haiku-5-5/whats-new-haiku-5-5
±changed
+1−1
apichanged
models/haiku-5-5/whats-new-haiku-5-5
| [`computer_20250124` returns an error on the Claude API, Claude Models on Google Cloud (Google managed), and Amazon Bedrock](https://platform.claude.com/docs/en/models/haiku-5-5/
| [`computer_20250124` returns an error](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset) on the Claude API, Claude Models on Google Cloud
+1 −1 lines
Recorded here 23 Oct 2026 00:07 UTC
models/fable-5-1/whats-new-fable-5-1
±changed
+5−5
apichanged
models/fable-5-1/whats-new-fable-5-1
Multilingual performance is comparable to Claude Fable 5.
Multilingual performance is at the same level as Claude Fable 5's.
* **Claude API:** all customers, as `claude-fable-5-1`.
* **AWS:** [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), as `anthropic.claude-fable-5-1`, and [Claude Platform on AWS]
* **Google Cloud:** [Claude Models on Google Cloud (Anthropic managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/anthropic-managed), as `
+5 −5 lines
Recorded here 23 Oct 2026 00:07 UTC
models/fable-5-1/migration-guide
±changed
+3−3
apichanged
models/fable-5-1/migration-guide
* **Context window and output:** A [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, and up to 128k output tokens per req
* **Context window and output:** A [1M token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows) by default, and up to 128k output tokens for eac
* **Data retention:** Both models require 30-day data retention, aren't available under zero data retention (ZDR) arrangements unless expressly authorized by Anthropic, and are des
* **Data retention:** Both models require 30-day data retention, aren't available under zero data retention (ZDR) arrangements unless expressly authorized by Anthropic, and are des
model: 'claude-fable-5',
+3 −3 lines
Recorded here 23 Oct 2026 00:07 UTC
managed-agents/workflow-runs
±changed
+1−1
apichanged
managed-agents/workflow-runs
| `workflow_run.status_running` | When the run starts running, which can be a while after `created`, and each time it resumes after a pause at the budget
| `workflow_run.status_running` | When the run starts its work, which can be a while after `created`, and each time it resumes after a pause at the budge
+1 −1 lines
Recorded here 23 Oct 2026 00:07 UTC
managed-agents/tools-web-restrictions
±changed
+2−2
apichanged
managed-agents/tools-web-restrictions
* **One list for each entry:** Set either `allowed_domains` (java, php: `allowedDomains`; csharp, go: `AllowedDomains`) or `blocked_domains` (java, php: `blockedDomains`; csharp, g
* **At most one list on an entry:** Set either `allowed_domains` (java, php: `allowedDomains`; csharp, go: `AllowedDomains`) or `blocked_domains` (java, php: `blockedDomains`; csha
If the combined `allowed_domains` (java, php: `allowedDomains`; csharp, go: `AllowedDomains`) lists have no domain in common, the tool stays available to that agent, but every call
If the combined `allowed_domains` (java, php: `allowedDomains`; csharp, go: `AllowedDomains`) lists have no domain in common, the tool stays available to that agent, but every call
+2 −2 lines
Recorded here 23 Oct 2026 00:07 UTC
managed-agents/sessions
±changed
+2−2
apichanged
managed-agents/sessions
// Clear the system prompt for this session. Array access is load-bearing here:
// Clear the system prompt for this session. Array access is required here:
Creating a session without `initial_events` (java, php: `initialEvents`; csharp, go: `InitialEvents`) registers the session but does not start any work; the environment's sandbox b
Creating a session without `initial_events` (java, php: `initialEvents`; csharp, go: `InitialEvents`) registers the session but does not start any work; the environment's sandbox s
+2 −2 lines
Recorded here 23 Oct 2026 00:07 UTC
managed-agents/session-threads
±changed
+7−3
apichanged
managed-agents/session-threads
EventStreamParams.builder().sessionId(session.id()).build()
EventStreamParams.builder()
.sessionId(session.id())
.build()
EventListParams.builder().sessionId(session.id()).build()
+7 −3 lines
Recorded here 23 Oct 2026 00:07 UTC
No change matches that. Try a path fragment like hooks.
Every page
812 listed, page 5 of 9api 100
- api/compliance
- api/compliance/activities
- api/compliance/activities/list
- api/compliance/apps
- api/compliance/apps/artifacts
- api/compliance/apps/artifacts/download
- api/compliance/apps/artifacts/retrieve
- api/compliance/apps/chats
- api/compliance/apps/chats/delete
- api/compliance/apps/chats/files
- api/compliance/apps/chats/files/delete
- api/compliance/apps/chats/files/download
- api/compliance/apps/chats/files/retrieve
- api/compliance/apps/chats/generated_files
- api/compliance/apps/chats/generated_files/download
- api/compliance/apps/chats/generated_files/retrieve
- api/compliance/apps/chats/list
- api/compliance/apps/chats/messages
- api/compliance/apps/chats/messages/list
- api/compliance/apps/code
- api/compliance/apps/code/artifacts
- api/compliance/apps/code/artifacts/delete
- api/compliance/apps/code/artifacts/download
- api/compliance/apps/code/artifacts/list
- api/compliance/apps/code/artifacts/retrieve_version
- api/compliance/apps/projects
- api/compliance/apps/projects/attachments
- api/compliance/apps/projects/attachments/list
- api/compliance/apps/projects/collaborators
- api/compliance/apps/projects/collaborators/list
- api/compliance/apps/projects/delete
- api/compliance/apps/projects/documents
- api/compliance/apps/projects/documents/delete
- api/compliance/apps/projects/documents/metadata
- api/compliance/apps/projects/documents/retrieve
- api/compliance/apps/projects/list
- api/compliance/apps/projects/retrieve
- api/compliance/apps/sessions
- api/compliance/apps/sessions/local
- api/compliance/apps/sessions/local/list
- api/compliance/apps/sessions/local/messages
- api/compliance/apps/sessions/local/messages/list
- api/compliance/apps/sessions/local/retrieve
- api/compliance/apps/sessions/remote
- api/compliance/apps/sessions/remote/list
- api/compliance/apps/sessions/remote/messages
- api/compliance/apps/sessions/remote/messages/list
- api/compliance/groups
- api/compliance/groups/list
- api/compliance/groups/members
- api/compliance/groups/members/list
- api/compliance/groups/retrieve
- api/compliance/organizations
- api/compliance/organizations/list
- api/compliance/organizations/roles
- api/compliance/organizations/roles/list
- api/compliance/organizations/roles/permissions
- api/compliance/organizations/roles/permissions/list
- api/compliance/organizations/roles/retrieve
- api/compliance/organizations/settings
- api/compliance/organizations/settings/retrieve
- api/compliance/organizations/user_preferences
- api/compliance/organizations/user_preferences/list
- api/compliance/organizations/users
- api/compliance/organizations/users/list
- api/errors
- api/files
- api/files/delete
- api/files/download
- api/files/list
- api/files/retrieve_metadata
- api/files/upload
- api/ip-addresses
- api/messages
- api/messages/batches
- api/messages/batches/cancel
- api/messages/batches/create
- api/messages/batches/delete
- api/messages/batches/list
- api/messages/batches/results
- api/messages/batches/retrieve
- api/messages/count_tokens
- api/messages/create
- api/migration-2026-10-21
- api/models
- api/models/list
- api/models/retrieve
- api/opentelemetry/spans
- api/organization
- api/organization/api_keys
- api/organization/api_keys/list
- api/organization/api_keys/retrieve
- api/organization/api_keys/update
- api/organization/compliance_settings
- api/organization/compliance_settings/retrieve
- api/organization/compliance_settings/update
- api/organization/external_keys
- api/organization/external_keys/create
- api/organization/external_keys/delete
- api/organization/external_keys/list