AI BriefingVercel Blog news
The latest AI and developer news from Vercel Blog, with short summaries.
Visit website →Vercel Functions Expands Package Size Support Up to 5GB
Vercel Functions has increased the package size limit 20x, from 250MB to 5GB, strengthening support for AI and data libraries.
Query Speed Insights data via Vercel CLI
A new feature has been added that lets you directly query real-user-based Web Vitals and page performance metrics through the Vercel CLI.
Sandbox expiration criteria changed to last-used time
The expiration criteria for Vercel Sandbox snapshots has been changed from creation time to last-used time, improving management efficiency.
xAI Grok Audio Models Now Available on Vercel AI Gateway
xAI Grok's realtime voice, TTS, and STT models are now available through Vercel AI Gateway.
AI Gateway Begins Supporting Real-Time Voice, Speech, and Transcription Features
Vercel AI Gateway now supports real-time voice agents, TTS, and STT capabilities, available in beta through AI SDK 7.
Web Analytics Querying via Vercel CLI
You can now query web analytics data directly from the Vercel CLI using the vercel metrics command.
AI SDK 7
Vercel has released AI SDK 7, featuring enhanced reasoning control and context management capabilities to boost productivity in agent development.
Teaching agents product design at Vercel
Vercel built a 'product-design' system so agents can understand the design-decision context that doesn't make it into code.
AI SDK 7 Released
AI SDK 7 has evolved into a unified platform for building multimodal agents that goes beyond text.
Vercel Ship Berlin 2026 Summary
Vercel announced dedicated infrastructure and AI SDK 7 for building and deploying AI agents.
Deep Agents and OpenCode Added to AI SDK Harness
Vercel's AI SDK Harness adds Deep Agents and OpenCode adapters, providing unified support for various coding agent runtimes.
Vercel Flags, No SDK Key Setup Required for Vercel Deployments
When using Vercel Flags in a Vercel deployment environment, automatic authentication is now possible without configuring an SDK Key.
Pro teams can now run up to 500 concurrent builds
Vercel has significantly expanded concurrent build support on Pro and Enterprise plans, increasing the limit from 12 to 500.
GLM 5.2 Fast via Wafer, Now Available on AI Gateway
The high-performance Wafer-based GLM 5.2 Fast model is now available on Vercel AI Gateway.
Deploying Node.js Servers with Zero Configuration
Vercel now lets you instantly deploy a Node.js server with just a server.ts file, no separate configuration needed.
Vercel CLI now preserves local environment variables when linking
Vercel CLI has been updated so that running vercel link no longer overwrites existing variables in the .env.local file, preserving them instead.
Custom OIDC Token Audience Support
Vercel has strengthened security by issuing OIDC tokens with an Audience customized for specific services.
Trace Viewer Redesign for Vercel Workflows
Vercel has unveiled an improved Trace Viewer that allows precise inspection of workflow execution.
Deploy Instantly from Claude Design to Vercel
You can now instantly send designs made in Claude Design to Vercel and deploy them as a live URL.
Chat SDK Adds Linq Support
Chat SDK has begun supporting the Linq platform through a new official adapter.