AI BriefingVercel Blog news
The latest AI and developer news from Vercel Blog, with short summaries.
Visit website →AI Gateway Adds Support for Team and Project Spend Budgets
AI Gateway now supports setting spend budgets at the team and project level.
DeepSeek V4 Flash now runs on new weights by default on AI Gateway
DeepSeek V4 Flash now runs by default with new weights on AI Gateway.
Chat SDK adds reaction and ephemeral message support for Teams
Chat SDK's Teams adapter now supports reactions and per-user ephemeral messages.
AI Gateway adds a dedicated logs page
AI Gateway has added a logs page that shows per-request cost, token, and routing information.
Vercel MCP supports the 2026-07-28 MCP specification
Vercel MCP now supports the latest MCP specification without requiring any client changes.
AI Gateway increases capacity for Laguna S 2.1 by 10x
AI Gateway has increased processing capacity for both the paid and free versions of Laguna S 2.1 by 10x.
Vercel Observability Expands Workflow Run Search
Vercel Observability has added a feature to search workflow runs by detailed conditions.
Vercel Passport Officially Launched
Vercel has officially launched Passport, which secures deployments with its own authentication provider.
Server-Timing response header will be forwarded to the client
Starting August 10, 2026, Vercel CDN will forward the Server-Timing response header directly to the client.
Shopify and Vercel Rebuild Hydrogen for Faster Storefronts
Shopify and Vercel are partnering to introduce a new, framework-agnostic open source Hydrogen.
Running Multiple Isolated Agents Within a Single Sandbox
The @vercel/sandbox SDK now supports multi-user and group features, enabling isolated agents to run within a single Sandbox.
MiniMax H3 Now Available on AI Gateway
MiniMax H3 has been added to AI Gateway, supporting 2K resolution video generation through text and multimodal inputs.
Thinking Machines' Inkling Small Now Available on AI Gateway
Thinking Machines' lightweight model Inkling Small has been added to AI Gateway, enabling efficient inference and coding tasks.
Turborepo and Vercel Remote Cache Now Support OpenID Connect (OIDC)
Turborepo and Vercel Remote Cache now support OIDC, enhancing the security of CI/CD workflows.
AI Gateway: GPT-5.6 Price Cuts and Speed Update
AI Gateway has lowered the price of the GPT-5.6 models and improved the inference speed of the Sol model.
Deployment speed improved by up to 7 seconds
Vercel has reduced deployment times by up to 7 seconds through platform overhead reduction and CLI performance optimizations.
mcp-handler Releases Version 2.0 Supporting the Latest MCP Spec
mcp-handler 2.0 has been released, supporting the latest Model Context Protocol spec and TypeScript SDK v2.
Project-scoped Tokens
A project-scoped token feature has been added that limits permissions so access is restricted to a specific project's resources when using the Vercel API.
AI Gateway Adds Unified Fast Mode Support
AI Gateway has launched a unified Fast Mode in beta that provides lower latency and higher throughput on a per-model basis.
xAI's Grok Voice Think Fast 2.0 Now Available on AI Gateway
xAI's new speech-to-speech model, Grok Voice Think Fast 2.0, has launched on AI Gateway.