We've added capabilities.thinking.types.disabled to the Models API
We've added capabilities.thinking.types.disabled to the Models API. GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts thinking: {type: "disabled"}, which turns thinking off. See Using the Models API.
Also shipped Oct 5, 2026Anthropic in October 2026 →
Scheduled Search and Reporting is now generally available
New Relic is excited to share that Scheduled Search and Reporting is now generally available. Instead of manually re-running the same NRQL query to check on your data, Scheduled Search runs it for you, on whatever cadence you choose, and delivers the results straight to your inbox. What is Scheduled Search and Reporting?
Starting on July 1, 2026, Identity Service for GKE is deprecated in GKE version 1.36 and earlier
Starting on July 1, 2026, Identity Service for GKE is deprecated in GKE version 1.36 and earlier. This feature is also unavailable in organizations that were created on or after July 1, 2025. GKE version 1.37 and later don't support Identity Service for GKE.
GKE support for using the c4-standard-* machine types (up to 192 vCPUs) as Confidential GKE Nodes with Intel...
GKE support for using the c4-standard-* machine types (up to 192 vCPUs) as Confidential GKE Nodes with Intel TDX is generally available. For more information, see the following pages: To use this feature with GKE , see Encrypt workload data in-use with Confidential GKE Nodes .
AI Deep Scan with linked repositories | GitHub Cloud | Essentials and above, AI Deep Scan access, Beta
AI Deep Scan with linked repositories | You can now give AI Deep Scan context from linked repositories to analyze your primary repository more thoroughly. Source from dependencies, such as a shared authentication library, helps CodeRabbit investigate and verify security findings in the primary repository. Learn more in the linked repositories documentation .
Lyria 3 music models for your app's AI features
Your app's AI features can now generate music with two Google models, from a text prompt or an image, with vocals or as an instrumental: Lyria 3 Clip Preview , for clips of about 30 seconds. Lyria 3 Pro Preview , for full tracks up to 184 seconds. Ask Lovable to use either model in your app, or describe what you want and let Lovable pick.
More from Claude PlatformEvery Claude Platform release →
We've added capabilities.server_tools to the Models API
We've added capabilities.server_tools to the Models API. GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts the web search and code execution tools. To check whether a model accepts the code execution tool, read capabilities.server_tools.code_execution.
We've lowered the price of prompt cache reads on Claude Sonnet 5.5 from $0.20 USD to $0.10 USD per million
We've lowered the price of prompt cache reads on Claude Sonnet 5.5 from $0.20 USD to $0.10 USD per million tokens: 0.05x the base input price instead of 0.1x. Cache writes and all other prices are unchanged. See Prompt caching pricing.
We've launched Claude Haiku 5.5 (claude-haiku-5-5), our most capable model tuned for high-volume and
We've launched Claude Haiku 5.5 (claude-haiku-5-5), our most capable model tuned for high-volume and latency-sensitive work. It has a 1M token context window, 128k max output tokens, and adaptive thinking with the effort parameter.
Code written for Claude Haiku 4.5 can break on Claude Haiku 5.5
Code written for Claude Haiku 4.5 can break on Claude Haiku 5.5. Manual extended thinking (budget_tokens) returns a 400 error, and adaptive thinking is on by default, so a response can begin with thinking blocks. The same text also counts as more tokens. See the migration guide. For model-specific prompting patterns, see Prompting Claude Haiku 5.5.
The Python and TypeScript SDKs now include classes, in beta, for the browser use tool and the computer use
The Python and TypeScript SDKs now include classes, in beta, for the browser use tool and the computer use tool. You subclass one and write one method per tool against your own browser or desktop automation. The SDK runs the tool loop, the URL and file policies you set for the browser, and your approval callback.
Claude Max and Team plans now include monthly API credits
Claude Max and Team plans now include monthly API credits. To learn how to claim them, see API credits for Max and Team plans.
In Claude Managed Agents, a cloud environment with limited networking now also applies its allowed_hosts to
In Claude Managed Agents, a cloud environment with limited networking now also applies its allowed_hosts to the web_search and web_fetch tools. A web_fetch call for a URL on a host that allowed_hosts does not match returns a url_not_allowed error result to the agent. web_search omits results from such hosts.
With limited networking, creating a session fails with a 400 error when an enabled web tool's allowed_domains
With limited networking, creating a session fails with a 400 error when an enabled web tool's allowed_domains has an entry not within allowed_hosts. So does a session update that adds such an entry. An allowed_hosts entry matches one exact host unless it starts with *., so docs.example.com is not within ["example.com"].