Releasesby GlyphCompliance API adds Claude Science and Microsoft 365 session transcripts in beta
Local session endpoints now return transcripts of Claude Science sessions and Claude for Microsoft 365 sessions in Excel, PowerPoint, Word and Outlook, in beta for Claude Enterprise organizations.
Also shipped Aug 26, 2026Anthropic in August 2026 →
You can now view real-time logs for your Python UDFs in Cloud Logging
You can now view real-time logs for your Python UDFs in Cloud Logging. This feature is generally available .
Cortex Extension references in agent skills (General availability)
Referencing a Cortex Extension from an agent skill is now generally available. Set the skill source type to CORTEX_EXTENSION and path to the extension's fully qualified name, and Snowflake expands the reference into the extension's member skills at request time, so you don't list each skill individually.
Cortex Agents Coding Agent (General availability)
The Cortex Agents Coding Agent is now generally available. Add the code_toolset_all tool type to a Cortex Agent, and Snowflake provisions and manages a sandbox backed by the same runtime that powers Snowflake CoCo: bash, file read/write/edit, grep, glob, web search, SQL execution, and skills.
Organization user types (General availability)
With this release, you can specify whether an organization user represents a person or a service. Set the TYPE property to SERVICE for a service or application that interacts with Snowflake without human interaction. If you don't specify a type, the organization user is a PERSON user, which matches the previous behavior.
Semantic Studio (Preview)
Semantic Studio is now available in public preview for all accounts. Semantic Studio is the authoring environment for semantic views in Workspaces, combining conversational authoring with CoCo, direct YAML editing, and deployment to the live Snowflake object in a single surface.
Zerobus Ingest into streaming tables is now generally available
Ingesting into streaming tables with Zerobus Ingest in Lakeflow Connect is now generally available. Writing to a streaming table works the same way as writing to a managed Delta table, with the same limits and quotas. See Create or identify the target table .
More from Claude PlatformEvery Claude Platform release →
Admin API comes to the ant CLI and Claude SDKs under client.beta.organization
The ant CLI and the Python, TypeScript, C#, Go, Java, PHP and Ruby SDKs now cover Admin API resources including members, workspaces, API keys, rate limits, service accounts and encryption keys. Usage and cost reports remain curl-only.
Claude SDKs stop sending beta headers for Files and Skills clients
Python 1.2.0, TypeScript 0.122.0, Go 1.68.0, Java 2.59.0, Ruby 1.67.0 and C# 12.44.0 make client.beta.files and client.beta.skills match the GA shapes. client.beta.skills.delete() now removes all versions, and BetaSkill is renamed BetaContainerSkill.
Claude Console adds personal and service account API keys
Personal and service account keys act as a user or service account with the same permissions and stop working when that account leaves the organization. Admins can track usage per account, and keys can be scoped to one workspace or used on admin endpoints.
Claude Fable 5.1 launches alongside Claude Mythos 5.1 with 1M token context
Claude Fable 5.1 succeeds Claude Fable 5 for long-running agentic coding, knowledge work and research, with Claude Mythos 5.1 for Project Glasswing participants. Both have a 1M context, 128k output and adaptive thinking at $10 / $50 per MTok, with cache reads cut to $0.25 per MTok.
Prompt cache reads on Claude Fable 5.1 and Mythos 5.1 drop to $0.25 per MTok
Cache reads on Claude Fable 5.1 and Claude Mythos 5.1 cost 0.025x the base input price instead of the usual 0.1x, which lowers the cost of cache-heavy agent workloads. Cache write pricing is unchanged.
Claude Fable 5.1 and Mythos 5.1 reject tool_choice any and tool
On Claude Fable 5.1 and Claude Mythos 5.1, tool_choice types any and tool return a 400 error while auto and none are unchanged. Use strict tool use or structured outputs to guarantee schema-conformant tool inputs.
Claude Fable 5.1 thinking blocks only replay to the same or newer models
Thinking blocks from Claude Fable 5.1 and Mythos 5.1 can't be read by earlier models and are dropped if replayed to them. Fable 5.1 also checks that nothing before a replayed block has changed, which matters for agents that edit conversation history.
Per-message effort changes enter beta on the Claude API
A role system message carrying output_config.effort inside messages changes effort for later turns while preserving the prompt cache, on Claude Fable 5.1, Mythos 5.1 and Opus 5. Requests need the mid-conversation-output-config-2026-07-01 beta header.