♟️🏆 Chess Battle Our Vercel hackathon submission 70+ AI models face off in real-time chess tournaments. Every move validated, matches streamed live, Elo ratings updated on the fly. Built with: - Next.js 15 + React 19 - Vercel AI Gateway + AI SDK - Trigger.dev +

I won 3rd prize in the Vercel AI Gateway Hackathon with my Textual Games project! 🏆 Can't believe it! As promised, I'll remove the subscription and let everyone play for free until that prize money is gone! ⚔️

AI SDK 6 beta: reranking models Thanks Vivek Patel for the contribution!

Vercel has partnered with Z.ai to offer the lowest pricing for GLM 4.6. • Available via Vercel AI Gateway • $0.45 / M input tokens • $1.80 / M output tokens • Set the model to 𝚣𝚊𝚒/𝚐𝚕𝚖-𝟺.𝟼 to start building vercel.fyi/glm-4.6

AI SDK 6 beta: Anthropic + structured outputs + tool calling Thanks @AnkitVarsh16015 for the contribution!

MiniMax M2 is now on Vercel AI Gateway. • Free until Nov 7 2025 • Set model to 𝚖𝚒𝚗𝚒𝚖𝚊𝚡/𝚖𝚒𝚗𝚒𝚖𝚊𝚡-𝚖𝟸 • Open source model for agentic use Integrated in collaboration with MiniMax (official)'s engineering team to boost reliability & performance. vercel.com/changelog/mini…

Breakdown of most popular TLDs on the new vercel.domains. Domain purchases are up +34.6%, traffic +39.4%. The main innovation? Speed. When you make something fast, customers reward you.

OpenAI's new gpt-oss-safeguard model is now on Vercel AI Gateway. • Set model to 𝚘𝚙𝚎𝚗𝚊𝚒/𝚐𝚙𝚝-𝚘𝚜𝚜-𝚜𝚊𝚏𝚎𝚐𝚞𝚊𝚛𝚍-𝟸𝟶𝚋 • Open weight reasoning model • Fine-tuned for safety classification tasks, like content moderation vercel.com/changelog/open…

Vercel Agent has a new skill: incident response. It can now intelligently investigate anomalies to surface critical issues and speed up time to resolution. New Agent users can claim a $100 free credit. vercel.com/blog/vercel-ag…

This was a great game.

We’re hiring engineers for the Workflow DevKit team Vercel :)

We build Vercel on Vercel. Vercel AI Gateway runs on Fluid compute, on the same network as you: • Concurrency keeps CPUs hot, costs low • Billed for CPU only when active • Anycast routing for low latency • Redis + in-memory caching • Built-in o11y vercel.com/blog/how-ai-ga…

Vercel’s AI products like v0, Agent, and AI Gateway are built on Vercel. 🥵 Before: global accelerators (AGA), load balancers (NLB), TLS ingress (Nginx), Kubernetes (EKS / Karpenter), EC2, Terraform… 🌊 After: Fluid and 𝚐𝚒𝚝 𝚙𝚞𝚜𝚑 How to build your own Gateway,

Vercel Domains now supports AI search. Go beyond keywords, describe what you’re looking for. Try it now at vercel.com/domains

Name this game! You can do it right!? #gaming #RetroGaming #VideoGames

I wanted a really good GitHub agent for in-depth queries so built one last night - Can search all of GitHub (issues, code, etc) - Is personalized to you, i.e "which of my PRs have failing CI" - Has a sandbox to run commands in Hosted free at betterpilot.vercel.app

Currently the maximum upload size to Vercel Functions is 4.5 MB. A limit inherited from our past of using AWS Lambda directly. Thanks for the great Schlez this is about to go away! We're already testing higher limits on the AI Gateway (which is just another Vercel app), and

We have a NEW DEMO! This is exclusively for the new Procedural Survival Islands we've been working on. You get to play one such island, start from nothing, craft, fight, build, destroy, explore.. SP or co-op!

Access OpenAI's GPT-5.1 Codex models through the Vercel AI Gateway. • Tailored to long-running, agentic coding tasks to maintain context • Set model to 𝚘𝚙𝚎𝚗𝚊𝚒/𝚐𝚙𝚝-𝟻.𝟷-𝚌𝚘𝚍𝚎𝚡 or 𝚘𝚙𝚎𝚗𝚊𝚒/𝚐𝚙𝚝-𝟻.𝟷-𝚌𝚘𝚍𝚎𝚡-𝚖𝚒𝚗𝚒 vercel.com/changelog/gpt-…

Some company news. We’re relocating our headquarters from San Francisco to… San Francisco. The best place to build. We’ll be shipping from our new, much bigger, office on Monday 😁