Vercel Blog

adds a new command, giving direct access to the full suite of Vercel APIs from your terminal.vercel@50.5.1api The command provides a direct access point for AI...

Recraft models are now available via Vercel's with no other provider accounts required. You can access Recraft's image models, V3 and V2.AI Gateway These image...

The environment variables UI is now easier to manage across shared and project environment variables. You can spend less time scrolling, use larger hit targets,...

are now available in the and .AWS databasesVercel Marketplacev0 Read more...

Users can opt in to an experimental build mode for and projects.HonoExpress This mode lets you filter logs by route, similar to Next.js, and it updates the buil...

You can now trigger a Vercel Agent code review on demand. When Vercel post comments on your GitHub pull request, you can now click the button from the deploymen...

Vercel AI Gateway is a day 0 launch partner for the OpenResponses API, an open-source specification from OpenAI for multi-provider AI interactions. OpenResponse...

You can now open secure, interactive shell sessions to running Sandboxes with the .Vercel Sandbox CLI Note: While you’re connected, the Sandbox timeout is autom...

You can now give any model the ability to search the web using Perplexity through Vercel's AI Gateway. AI Gateway supports Perplexity Search as a universal web...

Today we're releasing a brand new set of components for AI Elements designed to work with the and functions of the AI SDK, helping you build the next generation...

You can now access GPT 5.2 Codex with Vercel's and no other provider accounts required. GPT 5.2 Codex combines GPT 5.2's strength in professional knowledge work...

We've encapsulated 10+ years of React and Next.js optimization knowledge into , a structured repository optimized for AI agents and LLMs. react-best-practices R...

Vercel Sandbox for Node.js now uses Node.js 24 by default. This keeps the Node.js runtime aligned with the latest Node.js features and performance improvements....

We shipped build system optimizations that reduce overhead for projects with many input files, large , or large build outputs.node_modules Expensive disk operat...

Models are powerful, but they're limited to their training data and knowledge cutoff date. When users ask about today's news, current prices, or the latest API...

It's a thrilling time to work in Sales at Vercel. The web is transitioning from pages to agents, and Vercel is building the self-driving infrastructure to power...

You can now set deployment suffixes at the project level, instead of using a single suffix across your team. Project-level suffixes follow the same requirements...

Vercel projects now support multiple secrets.Protection Bypass for Automation This makes it easier to rotate secrets and use different secrets for different wor...

Set team-wide defaults for Deployment Protection You can now set a team-wide default for .Deployment Protection New projects start with Deployment Protection se...

Projects that use now have increased limits for build caches.larger build machines These limit increases come at no additional charge. Learn more about .Vercel'...

We invited from to share how they shipped durable workflows with their .Dylan JhaveriMux@mux/ai SDK AI workflows have a frustrating habit of failing halfway thr...

Today, we're releasing a major update to Streamdown, our drop-in replacement for react-markdown, designed for AI-powered streaming. The most requested feature s...

Many of us have built complex tooling to feed our agents the right information. It's brittle because we're guessing what the model needs instead of letting it f...

On-Demand Concurrent Builds let builds skip the queue and run immediately, instead of waiting for other deployments to finish. You can now configure this featur...