One read of Claude Developer Platformapi-20261001T213726Z
336 pages moved out of 748 read.
Pages moved
336
significant first
Pages read
748
in this capture
Captured
21:37 UTC
Corpus hash
6a28c636443e
index-hash
What this read moved
326-336 of 336, page 14 of 14This capture is too large to show at once. Changes 326-336 of 336 are below, significant first; the rest are on the following screens.
cli-sdks-libraries/sdks/java Changed · +2 / -2 lines
from line 15
1515<Tabs>
1616 <Tab title="Gradle">
1717 ```kotlin
18 implementation("com.anthropic:anthropic-java:2.66.0")
18 implementation("com.anthropic:anthropic-java:2.67.0")
1919 ```
2020 </Tab>
2121
from line 24
2424 <dependency>
2525 <groupId>com.anthropic</groupId>
2626 <artifactId>anthropic-java</artifactId>
27 <version>2.66.0</version>
27 <version>2.67.0</version>
2828 </dependency>
2929 ```
3030 </Tab>
get-started Changed · +2 / -2 lines
from line 436
436436 }
437437
438438 dependencies {
439 implementation("com.anthropic:anthropic-java:2.66.0")
439 implementation("com.anthropic:anthropic-java:2.67.0")
440440 }
441441
442442 application {
from line 462
462462 <dependency>
463463 <groupId>com.anthropic</groupId>
464464 <artifactId>anthropic-java</artifactId>
465 <version>2.66.0</version>
465 <version>2.67.0</version>
466466 </dependency>
467467 </dependencies>
468468 </project>
manage-claude/spend-limits-api Changed · +2 / -2 lines
from line 114
114114
115115`GET /v1/organizations/spend_limits/effective` returns one row per current member, reflecting each member's effective spend limit, its `source` in the scope hierarchy, and their `period_to_date_spend`. Requires the `read:spend_limits` scope.
116116
117For complete parameter details and response schemas, see [List effective spend limits](https://platform.claude.com/docs/en/api/beta/organization/spend_limits/list_effective) in the API reference.
117For complete parameter details and response schemas, see [List effective spend limits](https://platform.claude.com/docs/en/api/beta/organization/spend_limits/effective/list) in the API reference.
118118
119119```bash cURL
120120curl "https://api.anthropic.com/v1/organizations/spend_limits/effective?limit=20" \
from line 162
162162
163163`POST /v1/organizations/spend_limits` sets a per-user spend limit override. This is an upsert keyed on `(scope, period)`: setting a limit for a user and period that already has one overwrites it in place. This endpoint accepts only `scope.type: "user"`; seat-tier, group, and organization-level defaults are configured in claude.ai settings. Requires the `write:spend_limits` scope.
164164
165For complete parameter details and response schemas, see [Create a spend limit](https://platform.claude.com/docs/en/api/beta/organization/spend_limits/create) in the API reference.
165For complete parameter details and response schemas, see [Create a spend limit](https://platform.claude.com/docs/en/api/beta/organization/spend_limits/set) in the API reference.
166166
167167```bash cURL
168168curl --request POST "https://api.anthropic.com/v1/organizations/spend_limits" \
manage-claude/user-management Changed · +2 / -2 lines
from line 388
388388
389389`POST /v1/organizations/rbac_groups/{rbac_group_id}/members` adds an organization member to the group by `user_id`. The user must already be a member of one of your enterprise's organizations (the request returns 404 otherwise), and adding someone who is already in the group returns 400. For `scim` groups, membership is managed in your identity provider and this request returns 400. To assign groups to a person who has not joined yet, use `rbac_group_ids` on [invite creation](https://platform.claude.com/docs/en/manage-claude/user-management#create-an-invite) instead. Requires the `write:rbac_groups` scope.
390390
391For complete parameter details and response schemas, see [Add group member](https://platform.claude.com/docs/en/api/beta/organization/rbac_groups/members/create) in the API reference.
391For complete parameter details and response schemas, see [Add group member](https://platform.claude.com/docs/en/api/beta/organization/rbac_groups/members/add) in the API reference.
392392
393393```bash cURL
394394curl -X POST "https://api.anthropic.com/v1/organizations/rbac_groups/rbac_group_01UvWxYzAbCdEfGhIjKlMn/members" \
from line 413
413413
414414`DELETE /v1/organizations/rbac_groups/{rbac_group_id}/members/{user_id}` removes the member from the group; they remain a member of their organization. The request returns 404 if the user is not a member of the group, and 400 for `scim` groups, whose membership is managed in your identity provider. Requires the `write:rbac_groups` scope.
415415
416For complete parameter details and response schemas, see [Remove group member](https://platform.claude.com/docs/en/api/beta/organization/rbac_groups/members/delete) in the API reference.
416For complete parameter details and response schemas, see [Remove group member](https://platform.claude.com/docs/en/api/beta/organization/rbac_groups/members/remove) in the API reference.
417417
418418```bash cURL
419419curl -X DELETE "https://api.anthropic.com/v1/organizations/rbac_groups/rbac_group_01UvWxYzAbCdEfGhIjKlMn/members/user_01AbCdEfGhIjKlMnOpQrSt" \
managed-agents/quickstart Changed · +2 / -2 lines
from line 43
4343 For Linux environments, download the release binary directly.
4444
4545 ```bash
46 VERSION=1.36.0
46 VERSION=1.37.0
4747 OS=$(uname -s | tr '[:upper:]' '[:lower:]')
4848 case $(uname -m) in
4949 x86_64) ARCH=amd64 ;;
from line 94
9494
9595 <Tab title="Java">
9696 ```groovy Gradle
97 implementation("com.anthropic:anthropic-java:2.66.0")
97 implementation("com.anthropic:anthropic-java:2.67.0")
9898 ```
9999 </Tab>
100100
managed-agents/self-hosted-sandboxes Changed · +2 / -2 lines
from line 221
221221 For Linux environments, download the release binary directly.
222222
223223 ```bash
224 VERSION=1.36.0
224 VERSION=1.37.0
225225 OS=$(uname -s | tr '[:upper:]' '[:lower:]')
226226 case $(uname -m) in
227227 x86_64) ARCH=amd64 ;;
from line 259
259259
260260 ```dockerfile
261261 FROM your-base-image
262 ARG ANT_VERSION=1.36.0
262 ARG ANT_VERSION=1.37.0
263263 ARG TARGETARCH
264264 RUN ARCH=$([ "$TARGETARCH" = "arm64" ] && echo arm64 || echo amd64) && \
265265 curl -fsSL "https://github.com/anthropics/anthropic-cli/releases/download/v${ANT_VERSION}/ant_${ANT_VERSION}_linux_${ARCH}.tar.gz" \
models/fable-5-1/migration-guide Changed · +1 / -1 lines
from line 1557
15571557
155815584. **Text between tool calls is returned in thinking blocks:** On Claude Opus 5, text the model writes between tool calls comes back as `text` blocks. On `claude-fable-5-1`, as on Claude Fable 5, that narration comes back as progress-update `thinking` blocks, one before each tool call. Under the default `thinking.display` of `"omitted"`, they carry no readable text. If your interface renders that narration, set `display: "updates"` (beta) to receive progress updates as text while reasoning stays hidden, or `"summarized"` to receive both. Then render the non-empty `thinking` blocks between `tool_use` blocks. See [Progress updates between tool calls](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates).
15591559
15605. **Safety classifiers and fallback routing:** Claude Fable 5.1 runs safety classifiers covering the same `stop_details` categories as Claude Fable 5, a broader set than Claude Opus 5's cybersecurity-only classifiers. Expect `stop_details.category` values beyond `"cyber"`, such as `"bio"` and `"reasoning_extraction"`; see the [refusal category table](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) for the full set. For `fallbacks` configuration and permitted targets, see [Use `fallbacks: "default"` for refusals](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#fable-5-1-recommended-changes).
15605. **Safety classifiers and fallback routing:** Claude Fable 5.1 runs safety classifiers covering the same `stop_details` categories as Claude Fable 5, a broader set than Claude Opus 5's classifiers. Expect additional `stop_details.category` values, such as `"bio"`; see the [refusal category table](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) for the full set. For `fallbacks` configuration and permitted targets, see [Use `fallbacks: "default"` for refusals](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#fable-5-1-recommended-changes).
15611561
156215626. **Pricing:** $10 USD per million input tokens and $50 USD per million output tokens, compared with $5 USD and $25 USD for Claude Opus 5. Prompt cache reads are $0.25 USD per million tokens, half the Claude Opus 5 rate. See [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing).
15631563
models/opus-5-5/whats-new-opus-5-5 Changed · +2 / -2 lines
from line 44
4444
4545### Thinking blocks are tied to the model and the conversation
4646
47Every thinking block records which model produced it, and each model reads its own blocks and only some other models'. Claude Opus 5.5 reads thinking blocks from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API, from Claude Sonnet 5.5, but not from Claude Fable or Claude Mythos models. On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read thinking blocks from Claude Opus 5.5; no other model does. A conversation that moves from Claude Opus 5 onto Claude Opus 5.5, or from Claude Opus 5.5 up to Claude Fable 5.1 or Claude Mythos 5.1 on the Claude API, keeps its reasoning. One that moves from Claude Opus 5.5 to any model other than those two, or onto it from a Claude Fable or Claude Mythos model, runs the turns after the switch without the previous model's reasoning. When a request carries a block the target model can't read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren't billed. With the `thinking-binding-controls-2026-08-01` beta header the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
47Every thinking block records which model produced it, and each model reads its own blocks and only some other models'. Claude Opus 5.5 reads thinking blocks from Claude Opus 5, from earlier Opus, Sonnet, and Haiku models, and, on the Claude API and Google Cloud, from Claude Sonnet 5.5, but not from Claude Fable or Claude Mythos models. On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read thinking blocks from Claude Opus 5.5; no other model does. A conversation that moves from Claude Opus 5 onto Claude Opus 5.5, or from Claude Opus 5.5 up to Claude Fable 5.1 or Claude Mythos 5.1 on the Claude API, keeps its reasoning. One that moves from Claude Opus 5.5 to any model other than those two, or onto it from a Claude Fable or Claude Mythos model, runs the turns after the switch without the previous model's reasoning. When a request carries a block the target model can't read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren't billed. With the `thinking-binding-controls-2026-08-01` beta header the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
4848
4949The API also checks whether anything before a Claude Opus 5.5 thinking block (the `system` prompt, the `tools`, or an earlier message) has changed since the block was produced. As on Claude Fable 5.1, it enforces that check by default for accounts created on or after August 31, 2026, 00:00 UTC, on the Claude API and on cloud platforms. On those accounts, a request that replays a block after such a change returns a 400 error. To drop the affected blocks instead, send the `thinking-binding-controls-2026-08-01` beta header and set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"`. On older accounts, setting that field to either value opts the request in. Keep the conversation append-only so the question never arises: change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) rather than edits. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) and the migration guide's [note on this change](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-blocks).
5050
from line 81
8181* **The default effort is `medium`.** A request that omits `effort` runs at `medium`; on Claude Opus 5 it ran at `high`. Set `effort` explicitly and re-run your sweep; see [Calibrate effort](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#calibrate-effort).
8282* **More thinking per turn at a given effort level.** At the same [effort](https://platform.claude.com/docs/en/build-with-claude/effort) setting the model tends to think more per turn than Claude Opus 5, most of all at `xhigh` and `max`. Re-run your effort sweep rather than carrying a setting over, and leave room in `max_tokens` for the thinking. See [Calibrate effort](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#calibrate-effort).
8383* **Text between tool calls comes back in thinking blocks.** The short notes the model writes between tool calls arrive as [progress-update `thinking` blocks](https://platform.claude.com/docs/en/build-with-claude/thinking#progress-updates) rather than `text` blocks, so at the default `display: "omitted"` an application that streams them to its users goes quiet between tool calls, with no error. The [migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#text-between-tool-calls) has the fix for receiving them, and [User-facing progress updates](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#user-facing-progress-updates) covers how to ask for more of them.
84* **More safeguard categories.** The model runs a biology safety classifier in addition to the cybersecurity one, and requests that push it to reproduce its internal reasoning in the response text can be declined with the `reasoning_extraction` category. See [Refusals and fallback](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#refusals-and-fallback) and [Safeguard refusals](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#safeguard-refusals).
84* **More safeguard categories.** The model runs a biology safety classifier in addition to the cybersecurity one. As on Claude Opus 5, requests that push it to reproduce its internal reasoning in the response text may be declined with the `reasoning_extraction` category. See [Refusals and fallback](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#refusals-and-fallback) and [Safeguard refusals](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#safeguard-refusals).
8585* **Sharper reading of charts, diagrams, and screenshots.** The model reads values off dense charts and layout-dependent visuals much more precisely without tools, so prompt-side vision workarounds built for earlier models may no longer be needed; image tools still add accuracy on the densest inputs. See [Tools for complex visual inputs](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#tools-for-complex-visual-inputs).
8686
8787If your Claude Opus 5 integration ran with thinking disabled, see [Prompts written for thinking disabled](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#prompts-written-for-thinking-disabled) alongside the [breaking change](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-cant-be-disabled). For the capability gains in agentic coding and code review, knowledge work, communication, visual inputs, and computer use, see [Capabilities relevant to prompting](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5-5#capability-improvements).
models/sonnet-5-5/whats-new-sonnet-5-5 Changed · +2 / -2 lines
from line 48
4848
4949### Thinking blocks are tied to the model and the conversation
5050
51Every thinking block records which model produced it. Each model reads its own blocks and only some other models' blocks. Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. On the Claude API, Claude Opus 5.5 reads Claude Sonnet 5.5 thinking blocks; no other model does.
51Every thinking block records which model produced it. Each model reads its own blocks and only some other models' blocks. Claude Sonnet 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models, but not from Claude Opus 5, Claude Opus 5.5, or any Claude Fable or Claude Mythos model. On the Claude API and Google Cloud, Claude Opus 5.5 reads Claude Sonnet 5.5 thinking blocks; no other model does.
5252
53So a conversation that moves from Claude Sonnet 5 onto Claude Sonnet 5.5, or from Claude Sonnet 5.5 up to Claude Opus 5.5 on the Claude API, keeps its reasoning, and any other move away from Claude Sonnet 5.5 runs the turns after the switch without it. When a request carries a block the target model can't read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren't billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
53So a conversation that moves from Claude Sonnet 5 onto Claude Sonnet 5.5, or from Claude Sonnet 5.5 up to Claude Opus 5.5 on the Claude API and Google Cloud, keeps its reasoning, and any other move away from Claude Sonnet 5.5 runs the turns after the switch without it. When a request carries a block the target model can't read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren't billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
5454
5555The API also checks whether anything before a Claude Sonnet 5.5 thinking block has changed since the block was produced: the `system` prompt, the `tools`, or an earlier message. It enforces that check by default for accounts created on or after August 31, 2026, 00:00 UTC, on the Claude API, Amazon Bedrock, and Google Cloud. On those accounts, a request that replays a block after such a change returns a 400 error. To drop the affected blocks instead, send the `thinking-binding-controls-2026-08-01` beta header and set `thinking.block_binding.prefix_mismatch_behavior` to `"drop_block"`. On older accounts, setting that field to either value opts the request in. `block_binding` works only with `thinking: {"type": "adaptive"}`. With `between_tools`, keep the history append-only, or strip the thinking blocks from the edited turn on.
5656
release-notes/overview Changed · +1 / -2 lines
from line 86
8686
8787* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) session endpoints are out of beta for Cowork and Claude Code sessions. See [Retrieve session transcripts](https://platform.claude.com/docs/en/manage-claude/compliance-sessions).
8888* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) local session endpoints now also return transcripts of Claude Science sessions (`product_surface` value `claude_science`) and Claude for Microsoft 365 sessions in Excel, PowerPoint, Word, and Outlook (`product_surface` values beginning with `office_agents`), in beta for Claude Enterprise organizations, with your existing Compliance Access Key and the `read:compliance_user_data` scope. See [Sessions on users' machines](https://platform.claude.com/docs/en/manage-claude/compliance-sessions#retrieve-local-sessions).
89
90- The [Admin API](https://platform.claude.com/docs/en/manage-claude/admin-api) is now available in the `ant` CLI and the Python, TypeScript, C#, Go, Java, PHP, and Ruby SDKs under `client.beta.organization`. They cover organization info, members, invites, workspaces and workspace members, API keys, rate limits, service accounts, workload identity federation issuers and rules, and customer-managed encryption keys. Usage and cost reports and the Claude Enterprise user-management and analytics endpoints remain curl-only. The CLI and SDKs read an Admin API key from `ANTHROPIC_API_KEY` or an `org:admin` OAuth token from `ANTHROPIC_AUTH_TOKEN`.
89* The [Admin API](https://platform.claude.com/docs/en/manage-claude/admin-api) is now available in the `ant` CLI and the Python, TypeScript, C#, Go, Java, PHP, and Ruby SDKs under `client.beta.organization`. They cover organization info, members, invites, workspaces and workspace members, API keys, rate limits, service accounts, workload identity federation issuers and rules, and customer-managed encryption keys. Usage and cost reports and the Claude Enterprise user-management and analytics endpoints remain curl-only. The CLI and SDKs read an Admin API key from `ANTHROPIC_API_KEY` or an `org:admin` OAuth token from `ANTHROPIC_AUTH_TOKEN`.
9190
9291### August 20, 2026
9392
test-and-evaluate/strengthen-guardrails/reduce-hallucinations Changed · +1 / -1 lines
from line 54
5454
5555## Advanced techniques
5656
57* **Chain-of-thought verification**: Ask Claude to explain its reasoning step-by-step before giving a final answer. This can reveal faulty logic or assumptions.
57* **Chain-of-thought verification**: Use [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) with `display: "summarized"`, and review the summarized reasoning in the `thinking` blocks when an answer looks wrong. This can reveal faulty logic or assumptions.
5858
5959* **Best-of-N verification**: Run Claude through the same prompt multiple times and compare the outputs. Inconsistencies across outputs could indicate hallucinations.
6060