Inference hooks are now in beta for Claude Enterprise organizations. Point Claude at your … 等 2 项
Aug 5, 2026Update soonOfficial source ↗ * **Inference hooks** are now in beta for Claude Enterprise organizations. Point Claude at your organization's AI security server, and each governed prompt across claude.ai, Cowork, and Claude Code is held for the server's allow or deny verdict before inference proceeds. Requests are signed, failure handling is configurable, and every denial is recorded in the compliance [Activity Feed](/docs/en/manage-claude/compliance-activity-feed). See [Inference hooks](/docs/en/manage-claude/inference-hooks).
- We've retired the Claude Opus 4.1 model (`claude-opus-4-1-20250805`). All requests to this model will now return an error. We recommend upgrading to [Claude Opus 5](/docs/en/about-claude/models/overview#latest-models-comparison). Researchers can request ongoing access through the [External Researcher Access Program](https://support.claude.com/en/articles/9125743-what-is-the-external-researcher-access-program).
Dreams (research preview) now supports Claude Opus 5. See Supported models.
Aug 1, 2026RecommendedOfficial source ↗ * [Dreams](/docs/en/managed-agents/dreams) (research preview) now supports Claude Opus 5. See [Supported models](/docs/en/managed-agents/dreams#limits).
We've launched Claude Opus 5 (claude-opus-5), a step-change improvement over Claude Opus 4… 等 6 项
Jul 24, 2026RecommendedOfficial source ↗ * We've launched **Claude Opus 5** (`claude-opus-5`), a step-change improvement over Claude Opus 4.8. Claude Opus 5 supports a [1M token context window](/docs/en/build-with-claude/context-windows) (both the default and the maximum), 128k max output tokens, and [thinking](/docs/en/build-with-claude/thinking) on by default, at $5 / $25 per MTok, the same pricing as Claude Opus 4.8. It's available on the Claude API, [Claude in Amazon Bedrock](/docs/en/build-with-claude/claude-in-amazon-bedrock), [Claude on Google Cloud](/docs/en/build-with-claude/claude-on-vertex-ai), and [Claude in Microsoft Foundry](/docs/en/build-with-claude/claude-in-microsoft-foundry). See [What's new in Claude Opus 5](/docs/en/about-claude/models/whats-new-opus-5) for new features, behavior changes, and migration guidance, and the [models overview](/docs/en/about-claude/models/overview) for complete specs.
* On Claude Opus 5, disabling thinking is allowed only at effort `high` or below: `thinking: {"type": "disabled"}` with effort `xhigh` or `max` returns a 400 error, a breaking change from Claude Opus 4.8. See [What's new in Claude Opus 5](/docs/en/about-claude/models/whats-new-opus-5#behavior-changes).
* [Effort](/docs/en/build-with-claude/effort) is the primary control for steering Claude Opus 5: the model supports the full ladder (`low`, `medium`, `high`, `xhigh`, `max`), with `max` for capability-critical work.
* Mid-conversation tool changes are now in beta on Claude Fable 5, Claude Mythos 5, Claude Opus 4.8, and Claude Opus 5: add or remove tools between turns of a conversation while preserving the prompt cache. Include the `mid-conversation-tool-changes-2026-07-01` beta header in your requests.
* The `fallbacks` parameter now supports a `"default"` mode, which applies Anthropic's recommended fallback models by refusal category. Server-side fallback is in beta, and the `"default"` mode requires the `server-side-fallback-2026-07-01` beta header. See [Refusals and fallback](/docs/en/build-with-claude/refusals-and-fallback).
* We've removed [fast mode](/docs/en/build-with-claude/fast-mode) for Claude Opus 4.7. Requests to `claude-opus-4-7` with `speed: "fast"` now return an error; unlike Claude Opus 4.6, they do not fall back to standard speed. Claude Opus 4.7 itself remains available at standard speed. To continue using fast mode, migrate to [Claude Opus 5](/docs/en/about-claude/models/migration-guide#migrating-from-claude-opus-47) or Claude Opus 4.8. Read more in [Fast mode](/docs/en/build-with-claude/fast-mode#supported-models).
You can now set an effort level on a Claude Managed Agents agent's model configuration. Pa… 等 5 项
Jul 22, 2026RecommendedOfficial source ↗ * You can now set an `effort` level on a Claude Managed Agents agent's model configuration. Pass `effort` inside the `model` object when you [create the agent](/docs/en/managed-agents/agent-setup#create-an-agent). See [Effort levels](/docs/en/build-with-claude/effort#effort-levels) for what each level does.
* Webhooks for Claude Managed Agents now cover the environment and memory store lifecycle: four `environment.*` event types and three `memory_store.*` event types. You can react to environment and memory store lifecycle changes without polling. See the Environment events and Memory store events tabs in [Subscribe to webhooks](/docs/en/managed-agents/webhooks#supported-event-types).
* When creating a Claude Managed Agents session, you can now [seed it with initial events](/docs/en/managed-agents/sessions#seed-the-session-with-initial-events). Pass `initial_events` on `POST /v1/sessions` with up to 50 `user.message` and `user.define_outcome` events. A non-empty list starts the agent loop in the same call, so you don't need a separate send-events request to start work.
* The `version` field is now optional when [updating a Claude Managed Agents agent](/docs/en/managed-agents/agent-setup#update-an-agent). Supply it for optimistic concurrency (a mismatch returns a 409 error), or omit it to apply the update unconditionally. See [Update semantics](/docs/en/managed-agents/agent-setup#update-semantics).
* Claude Managed Agents session thread event streams now support [event deltas](/docs/en/managed-agents/events-and-streaming#event-deltas). `GET /v1/sessions/{session_id}/threads/{thread_id}/stream` accepts the same `event_deltas[]` query parameter as the session-level stream, so you can preview a subagent's text as the model generates it. A connection previews only the thread it's reading. See [Preview session thread events](/docs/en/managed-agents/events-and-streaming#preview-session-thread-events).
The legacy Workbench (platform.claude.com/workbench) in the Claude Console is being sunset… 等 2 项
Jul 17, 2026Update soonOfficial source ↗ * The legacy **Workbench** ([platform.claude.com/workbench](https://platform.claude.com/workbench)) in the Claude Console is being sunset with access ending on August 17, 2026. Saved prompts, variables, and evals are not supported in the updated [Workbench](https://platform.claude.com/playground). You can export any data you want to keep from the banner and under your **Organizational Settings**. For more, see [How do I use the Workbench?](https://support.claude.com/en/articles/8606378-how-do-i-use-the-workbench) in the Claude Help Center.
* The experimental prompt tools APIs for generating, improving, and templatizing prompts (`/v1/experimental/generate_prompt`, `/v1/experimental/improve_prompt`, and `/v1/experimental/templatize_prompt`) are being retired along with the Workbench on August 17, 2026. After removal, requests to these endpoints will return an error.
Mid-conversation system messages are available on Claude Fable 5, Claude Mythos 5, and Cla…
Jul 15, 2026RecommendedOfficial source ↗ * [Mid-conversation system messages](/docs/en/build-with-claude/mid-conversation-system-messages) are available on Claude Fable 5, Claude Mythos 5, and Claude Opus 4.8, on the Claude API, [Claude in Amazon Bedrock](/docs/en/build-with-claude/claude-in-amazon-bedrock), and [Google Cloud](/docs/en/build-with-claude/claude-on-vertex-ai). No beta header is required. This corrects earlier availability notes.
You can now manage the people in your Claude Enterprise (claude.ai) organization with the …
Jul 14, 2026OptionalOfficial source ↗ * You can now manage the people in your **Claude Enterprise** (claude.ai) organization with the [Admin API](/docs/en/api/admin), in beta for all Claude Enterprise organizations: list members and look them up by email address, change a member's role, remove members, send and withdraw invites, manage groups and their membership, and read custom roles. Group and custom-role requests require the `anthropic-beta: ce-user-management-2026-07-13` beta header; member and invite requests take no beta header. An Admin API key with the `read:org_audit` scope can also call every user-management `GET` endpoint. See [User management](/docs/en/manage-claude/user-management).
Dreams (research preview) now supports Claude Fable 5 and Claude Sonnet 5. See Supported m… 等 2 项
Jul 10, 2026RecommendedOfficial source ↗ * [Dreams](/docs/en/managed-agents/dreams) (research preview) now supports Claude Fable 5 and Claude Sonnet 5. See [Supported models](/docs/en/managed-agents/dreams#limits).
* We've expanded the [Access Transparency](/docs/en/manage-claude/access-transparency) documentation of `cmek_preserve` events with a filter example, an example event payload, and two preservation reason codes (`policy_violation_investigation`, `csae_report`). The documentation now also clarifies that a preservation event is written whether the preservation was initiated by a human reviewer or an automated safety pipeline. See [CMEK content preservation](/docs/en/manage-claude/access-transparency#cmek-content-preservation).
You can now set an expiration when you create an API key or an Admin API key in the Claude…
Jul 8, 2026RecommendedOfficial source ↗ * You can now set an expiration when you create an API key or an Admin API key in the [Claude Console](https://platform.claude.com/settings/keys). Choose a preset, a custom duration, or **Never**. For keys with a lifetime of at least 7 days, Anthropic emails the creator before expiration. Existing keys are unaffected. The Admin API reports each key's expiration in the [`expires_at`](/docs/en/api/admin/api_keys/list) field. See [Authentication](/docs/en/manage-claude/authentication#key-expiration).