Releasesby GlyphConfigure where run state lives in Vercel Workflows
Vercel Workflows now keeps each run's state, queue dispatch, and output streams in a single home region: the region where the run starts by default, or any target region you choose.
Also shipped Jul 20, 2026Vercel in July 2026 →
Lakehouse : Cross-cloud Lakehouse now supports integration with SAP Business Data Cloud (BDC) in Preview
Lakehouse : Cross-cloud Lakehouse now supports integration with SAP Business Data Cloud (BDC) in Preview. This update includes the following features: Federation from SAP BDC: Create Delta Sharing catalogs in Lakehouse to automatically synchronize shares, schemas, and tables from SAP BDC.
OIDC federated authentication (Public Preview)
OpenID Connect (OIDC) security integrations for federated single sign-on (SSO) are available in Public Preview. Multiple OIDC integrations, or OIDC alongside an existing SAML2 integration, require identifier-first login . Without identifier-first login, only one SSO integration (SAML2 or OIDC) can be ENABLED=TRUE at a time.
DML into frozen regions of dynamic tables (General availability)
You can now use DML statements (INSERT, UPDATE, MERGE, DELETE) to modify rows directly in the frozen region of a dynamic table. This enables use cases such as GDPR-required row deletions or correcting specific records without triggering a full refresh of the active region. For more information, see DML into a frozen region .
Pass-through policies for dynamic tables with incremental refresh (General availability)
Dynamic tables that have base tables with arbitrary masking or row access policies can now maintain incremental refresh when the policy is pass-through for the role used during refresh (that is, when the refresh role has unrestricted access to all rows and columns regardless of the policy condition).
[In preview] Public Preview: Protect sensitive generative AI telemetry in Application Insights and Microsoft Foundry
Azure Monitor Application Insights now stores generative AI content in a dedicated GenAIContent table (AppGenAIContent in Log Analytics), making it possible to apply newly available access controls to sensitive AI telemetry. Because Application Insights p
AI credit pools for cost centers in the billing UI
You can now manage a cost center’s AI credit pool directly in the billing UI where you create and edit cost centers. Previously, you could only manage this through the GitHub REST API. This feature is available for Copilot Business and Copilot Enterprise on GitHub Enterprise Cloud. Toggle the AI credit pool on when you create or edit a cost center.
More from AI SDK and AI GatewayEvery AI SDK and AI Gateway release →
Laguna S 2.1 is now available on AI Gateway
Laguna S 2.1 from Poolside is now available on AI Gateway. There are 2 versions of the model available: Free version (256K context window): poolside/laguna-s-2.1-free Paid version (1M context window): poolside/laguna-s-2.1 Laguna S 2.1 is an open-weight Mixture-of-Experts model that supports a context window of up to 1M tokens and runs in thinking and...
Gemini 3.6 Flash and Gemini 3.5 Flash-Lite are now available on AI Gateway
Gemini 3.6 Flash and Gemini 3.5 Flash-Lite are now available on AI Gateway. Gemini 3.6 Flash improves quality across coding, agentic tasks, and web development while consuming fewer tokens and making fewer model calls. It produces cleaner web and app development output.
Service tiers now available on AI Gateway
AI Gateway now supports service tiering. Service tiers let you optimize for latency, throughput, and cost per request to match your use case. Pick a faster tier for interactive workloads (less queueing, higher token throughput), or a lower cost tier for background jobs that can tolerate more latency.
AI Gateway now supports streaming transcription
AI Gateway now supports streaming transcription . Previously, transcription required a complete audio file and returned the full transcript in a single response. Now you can stream audio in as it's captured and get transcript updates back as the model produces them, keeping latency low for uses like live captioning and voice input.
Extend eve agents with installable extensions
You can now package tools, connections, skills, instructions, and hooks into extensions that any eve agent can import. Extensions can be published to package registries, then installed, versioned, and upgraded like any other project dependency.
Connect to and manage Sandboxes from the dashboard
You can now connect to any running Sandbox from the Vercel dashboard. Run commands, browse the filesystem, upload and download files, and inspect open ports without leaving the browser. From the same view, you can also manage the sandbox lifecycle: take snapshots, and stop or resume persistent sandboxes. Open the Connect tab on any sandbox to try it out.
Ling 3.0 Flash is now available on AI Gateway
Ling 3.0 Flash from Ant Group is now available on AI Gateway. The model is free to use for the next three weeks, through August 3rd. Ling 3.0 Flash is a Mixture-of-Experts model with 124B total parameters and about 5.1B active per token. It has a 256K token context window and runs in thinking and non-thinking modes.
Data downloaded by Vercel Sandbox is now free
Vercel Sandbox no longer bills for data it downloads from the internet. Installing packages, cloning a Git repository, or pulling artifacts and datasets from an external source does not count toward Sandbox Data Transfer usage. Traffic received on a Sandbox's exposed ports is still billable, as is outbound traffic the Sandbox sends to the internet.