What's new in Claude

Claude API·Jun 9, 2026

Claude Fable 5 and Claude Mythos 5 use the tokenizer introduced with Claude Opus 4.7

Compared to models before Claude Opus 4.7, the same text produces roughly 30% more tokens. The exact increase depends on the content and workload shape. Use the token counting API with model: "claude-fable-5" to measure your prompts under the new tokenizer. Claude Fable 5 runs safety classifiers on requests and during response generation. The stop_details.category field on refusal responses now includes "reasoning_extraction" on Claude Fable 5, returned when a request is blocked under Anthropic's Terms of Service restrictions on reverse engineering or duplicating model outputs. On Claude Fable 5 and Claude Mythos 5, adaptive thinking is the only thinking mode: thinking: {"type": "disabled"} is not supported, and manual extended thinking budgets and assistant prefill are not supported (both return a 400 error). On Claude Fable 5 and Claude Mythos 5, thinking.display defaults to "omitted", the same as Claude Opus 4.8, Claude Opus 4.7, and Claude Mythos Preview; set display: "summarized" to receive readable thinking summaries. Claude Fable 5 requires 30-day data retention and is not available under zero data retention. Claude Managed Agents now supports scheduled deployments, letting you run sessions on a cron schedule without managing your own scheduler. Claude Managed Agents vaults now support environment variable credentials, so you can securely inject secrets into the agent's sandbox for CLIs, SDKs, and other services that authenticate through environment variables. The Compliance API Activity Feed (GET /v1/compliance/activities) is now available on Claude Platform on AWS. The session.thread_* webhook events now include a session_thread_id field identifying the multiagent thread that triggered the event. We've released a Swift package in beta that adds Claude as a server-side LanguageModel in Apple's Foundation Models framework.

Claude apps·Jun 9, 2026Announcement

Claude Fable 5 launch

We launched Claude Fable 5, a Mythos-class model that we’ve made safe for general use.

New model·Jun 9, 2026Announcement

New models: Claude Fable 5 and Claude Mythos 5

We've launched Claude Fable 5 (claude-fable-5), our most capable widely released model, alongside Claude Mythos 5 (claude-mythos-5) for Project Glasswing participants. Both models support a 1M token context window by default, 128k max output tokens, and always-on adaptive thinking.

Claude Code·Jun 8, 2026

Claude Code 2.1.169

Added --safe-mode flag (and CLAUDE_CODE_SAFE_MODE) to start Claude Code with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled for troubleshooting. Added /cd command to move a session to a new working directory without breaking the prompt cache mid-session.

Claude Code·Jun 6, 2026

Claude Code 2.1.168

Bug fixes and reliability improvements.

Claude Code·Jun 6, 2026

Claude Code 2.1.167

Bug fixes and reliability improvements.

Claude Code·Jun 6, 2026

Claude Code 2.1.166

Added fallbackModel setting to configure up to three fallback models tried in order when the primary model is overloaded or unavailable; --fallback-model now also applies to interactive sessions. Added glob pattern support in deny rule tool-name position ("*" denies all tools); allow rules reject non-MCP globs, and unknown tool names in deny rules warn at startup.

Claude Code·Jun 5, 2026

Claude Code 2.1.165

Bug fixes and reliability improvements.

Claude API·Jun 5, 2026

We announced the deprecation of the Claude Opus 4.1 model, with retirement on the Claude API scheduled for…

We recommend migrating to Claude Opus 4.8. Read more in Model deprecations.

Claude Code·Jun 4, 2026

Claude Code 2.1.163

Added requiredMinimumVersion and requiredMaximumVersion managed settings — Claude Code refuses to start if its version is outside the allowed range and directs the user to an approved version. Added /plugin list command to list installed plugins, with --enabled/--disabled filters.

Claude Code·Jun 3, 2026

Claude Code 2.1.162

claude agents --json now includes waitingFor showing what a waiting session is blocked on (e.g. permission prompt). --tools: explicitly listing Grep/Glob now provides the dedicated search tools on native builds with embedded search (previously these names were silently ignored).

Claude Code·Jun 2, 2026

Claude Code 2.1.161

[VSCode] Added a tip suggesting disabling terminal GPU acceleration (or running /terminal-setup) to fix garbled glyphs.

Claude Code·Jun 2, 2026

Claude Code 2.1.160

Added a prompt before writing to shell startup files (.zshenv, .zlogin, .bash_login) and ~/.config/git/, which could otherwise lead to unintended command execution.

Claude API·Jun 2, 2026

The advisor tool now supports a max_tokens parameter to cap the advisor model's output per call, reducing…

Set tools[].max_tokens on the advisor tool definition; see Capping advisor output. On the Claude API, you are no longer billed for a request when it returns stop_reason: "refusal" without Claude having generated any output.

Claude apps·Jun 2, 2026

Enterprise plans can manage admin permissions with custom roles

We extended the existing custom roles framework by adding admin permissions. Admin permissions give members access to specific administrative areas, like billing or privacy, without the need to make them Owners.

Claude Code·May 31, 2026

Claude Code 2.1.159

Internal infrastructure improvements (no user-facing changes).

Claude Code·May 30, 2026

Claude Code 2.1.158

Auto mode is now available on Bedrock, Vertex, and Foundry for Opus 4.7 and Opus 4.8. Opt in by setting CLAUDE_CODE_ENABLE_AUTO_MODE=1.

Claude Code·May 29, 2026

Claude Code 2.1.157

Added claude plugin init to scaffold a new plugin in .claude/skills. Added autocomplete for /plugin arguments: subcommands, installed plugin names, and plugins from known marketplaces.

Claude Code·May 29, 2026

Claude Code 2.1.156

Fixed an issue when using Opus 4.8 where thinking blocks were modified, leading to API errors.

Claude API·May 29, 2026

Claude Managed Agents webhooks, multiagent orchestration, and self-hosted sandboxes are now available on…

Claude Code·May 28, 2026

Claude Code 2.1.154

Added Claude Opus 4.8 support and 4.7 → 4.8 migration guidance to the /claude-api skill.

Claude Code·May 28, 2026

Claude Code 2.1.153

Added skipLfs option to github/git plugin marketplace sources to skip Git LFS downloads during clone and update.

Claude API·May 28, 2026

We've launched mid-conversation system messages

On Claude Opus 4.8, you can send role: "system" messages after a user turn (subject to placement rules) in the messages array, preserving prompt cache hits when instructions change during a long-running session. No beta header is required. The stop_details field on refusal responses is now publicly documented; it returns a category (cyber, bio, or null) and a human-readable explanation, so your application can route different classes of refusal to the right next step. On Claude Opus 4.8, the effort parameter defaults to high across all surfaces, including Claude Code and the Messages API. On Claude Opus 4.8, the minimum cacheable prompt length for prompt caching is 1,024 tokens, lower than on Claude Opus 4.7. With adaptive thinking enabled, Claude Opus 4.8 triggers reasoning only when a turn needs it, reducing wasted thinking tokens compared to Claude Opus 4.7 at the same effort level. Claude Opus 4.8 supports high-resolution image input (up to 2576 pixels on the long edge), same as Claude Opus 4.7. Task budgets now support Claude Opus 4.8. The advisor tool now supports Claude Opus 4.8. Computer use now supports Claude Opus 4.8. Fast mode for Claude Opus 4.8 is available as a research preview on the Claude API only. Setting the sampling parameters temperature, top_p, or top_k to a non-default value returns a 400 error on Claude Opus 4.8, same as on Claude Opus 4.7. In Claude Code, we've expanded Auto mode to more users for long-running tasks. In Claude Code, Max plan users now default to fast mode on Claude Opus 4.8. In Claude Code, Workflows are available as a research preview, letting you define and run multistep agentic plans. We've deprecated fast mode for Claude Opus 4.6, with removal approximately 30 days after launch. For updates to claude.ai, Cowork, Claude for Microsoft 365, and other Claude apps in this release, see the release notes for Claude Apps.

Claude apps·May 28, 2026Announcement

Claude Opus 4.8 launch, plus 1 more change

We’ve upgraded Claude Opus to a new version. Claude Opus 4.8 shows improvements over Opus 4.7 in coding, agentic skills, reasoning, and practical knowledge work tasks. We added connector permissions to extend the existing custom roles framework and allow administrators to control which connectors, and which individual tools on those connectors, are available to each custom role.

New model·May 28, 2026Announcement

New model: Claude Opus 4.8

We've launched Claude Opus 4.8 (claude-opus-4-8), our most capable widely released model. Claude Opus 4.8 supports a 1M token context window by default on the Claude API, Amazon Bedrock, Google Cloud, and Microsoft Foundry, 128k max output tokens, and the same set of tools and platform features as Claude Opus 4.7.

Claude Code·May 27, 2026

Claude Code 2.1.152

Added /reload-skills command to re-scan skill directories without restarting the session. Added a MessageDisplay hook event that lets hooks transform or hide assistant message text as it is displayed.

Claude API·May 27, 2026

The Messages API response now includes usage.output_tokens_details.thinking_tokens, reporting how many of…

When streaming, the breakdown appears only on the final message_delta event. No beta header is required.

Claude Code·May 23, 2026

Claude Code 2.1.150

Internal infrastructure improvements (no user-facing changes).

Claude Code·May 22, 2026

Claude Code 2.1.149

Enterprise: added the allowAllClaudeAiMcps managed setting to load claude.ai cloud MCP connectors alongside managed-mcp.json.