Updatespage 7 of 7
Claude product updates
210 articles
Claude Code 2.1.170
- Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Fable’s capabilities exceed those of any model we’ve ever made generally available. Update to version 2.1.170 f
Claude Fable 5 launch
We launched Claude Fable 5, a Mythos-class model that we’ve made safe for general use. For more information, see our blog post: Claude Fable 5 and Claude Mythos 5.
MCP tunnels is now available as a research preview, so you can connect to MCP se
MCP tunnels is now available as a research preview, so you can connect to MCP servers in your private network.
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` comman
Claude Code 2.1.168
- Bug fixes and reliability improvements
We announced the deprecation of the Claude Opus 4.1 model (claude-opus-4-1-20250
We announced the deprecation of the Claude Opus 4.1 model (claude-opus-4-1-20250805), with retirement on the Claude API scheduled for August 5, 2026. We recommend migrating to Claude Opus 4.8. Read mo
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
Claude Code 2.1.167
- Bug fixes and reliability improvements
Claude Code 2.1.165
- Bug fixes and reliability improvements
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 -
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 t
The Messages API response now includes usage.output_tokens_details.thinking_toke
The Messages API response now includes usage.output_tokens_details.thinking_tokens, reporting how many of the billed output tokens were extended thinking. When streaming, the breakdown appears only on
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 too
With adaptive thinking enabled, Claude Opus 4.8 triggers reasoning only when a t
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.
The stop_details field on refusal responses is now publicly documented; it retur
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
On the Claude API, you are no longer billed for a request when it returns stop_r
On the Claude API, you are no longer billed for a request when it returns stop_reason: "refusal" without Claude having generated any output. See Streaming refusals for detecting and handling refusals.
The advisor tool now supports a max_tokens parameter to cap the advisor model's
The advisor tool now supports a max_tokens parameter to cap the advisor model's output per call, reducing latency and output token cost for workloads that don't need full-length advisor responses. Set
Claude Code 2.1.161
- `OTEL_RESOURCE_ATTRIBUTES` values are now included as labels on metric datapoints, so you can slice usage metrics by custom dimensions like team or repo - `claude agents` rows now show `done/total`
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 - `acceptEdits` mode now p
Mid-conversation system messages (Claude Opus 4.8)
We've launched mid-conversation system messages. On Claude Opus 4.8, you can send role: "system" messages at non-first positions in the messages array, preserving prompt cache hits when instructions c
Claude Opus 4.8 launched (1M context, 128k output by default)
We've launched Claude Opus 4.8 (claude-opus-4-8), our most capable generally available model. Claude Opus 4.8 supports a 1M token context window by default, 128k max output tokens, and the same set of
Claude Managed Agents: webhooks, multiagent orchestration, self-hosted sandboxes on AWS
Claude Managed Agents webhooks, multiagent orchestration, and self-hosted sandboxes are now available on Claude Platform on AWS. See IAM actions for Claude Platform on AWS for the new IAM actions and
Anthropic Updates Roundup - 2026/05 (18 items)
A monthly roundup of 18 Anthropic updates in 2026/05
Claude Code 2.1.157
- Plugins in `.claude/skills` directories are now automatically loaded, no marketplace required - Added `claude plugin init <name>` to scaffold a new plugin in `.claude/skills` - Added autocomplete fo
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 2.1.159
- Internal infrastructure improvements (no user-facing changes)
Claude now works with more security and compliance tools
We introduced Claude Compliance API integrations with notable security and compliance tools. Now IT and security teams can govern Claude across our platform and suite of products, the same way they go
Enterprise plans can manage connector access with custom roles
Connector permissions now extend the custom roles framework, letting administrators control which connectors and individual tools are available to each custom role on Enterprise plans.
Claude Opus 4.8 launch
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. For more information, see our bl
Claude News Roundup, May 2026: Code with Claude, PwC, Small Business
Major Claude news as of May 2026: Code with Claude 2026 (agent-infrastructure focus), the expanded PwC partnership, the Claude for Small Business launch, and developer-platform updates — based on official announcements.