Qwen 3.8 Max is available on AI Gateway.
It scores mid-pack on the DeepsecBench cybersecurity leaderboard at one of the lowest costs per run.
𝚖𝚘𝚍𝚎𝚕: '𝚊𝚕𝚒𝚋𝚊𝚋𝚊/𝚚𝚠𝚎𝚗𝟹.𝟾-𝚖𝚊𝚡'
Grok's realtime voice is now on AI Gateway. Build with AI SDK 7:
• 𝚡𝚊𝚒/𝚐𝚛𝚘𝚔-𝚟𝚘𝚒𝚌𝚎-𝚝𝚑𝚒𝚗𝚔-𝚏𝚊𝚜𝚝-𝟷.𝟶 (𝚞𝚜𝚎𝚁𝚎𝚊𝚕𝚝𝚒𝚖𝚎)
• 𝚡𝚊𝚒/𝚐𝚛𝚘𝚔-𝚝𝚝𝚜 (𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚂𝚙𝚎𝚎𝚌𝚑)
• 𝚡𝚊𝚒/𝚐𝚛𝚘𝚔-𝚜𝚝𝚝 (𝚝𝚛𝚊𝚗𝚜𝚌𝚛𝚒𝚋𝚎)
eve is an open-source agent framework for building and scaling agents.
▪︎ Durable execution
▪︎ Sandboxed compute
▪︎ Human-in-the-loop
▪︎ Subagents and evals
Available now in public preview ↓
Grok Imagine Video 1.5 on AI Gateway.
Image-to-video generation with synced audio in one pass.
𝚊𝚠𝚊𝚒𝚝 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚅𝚒𝚍𝚎𝚘({
𝚖𝚘𝚍𝚎𝚕: '𝚡𝚊𝚒/𝚐𝚛𝚘𝚔-𝚒𝚖𝚊𝚐𝚒𝚗𝚎-𝚟𝚒𝚍𝚎𝚘-𝟷.𝟻-𝚙𝚛𝚎𝚟𝚒𝚎𝚠',
𝚙𝚛𝚘𝚖𝚙𝚝: '𝚊 𝚛𝚊𝚋𝚋𝚒𝚝 𝚜𝚙𝚛𝚒𝚗𝚝𝚒𝚗𝚐 𝚝𝚑𝚛𝚘𝚞𝚐𝚑 𝚗𝚢𝚌'
});
Claude Opus 4.8 is available on AI Gateway.
Improved long-horizon agentic coding, debugging, and writing over previous Opus models.
𝚖𝚘𝚍𝚎𝚕: '𝚊𝚗𝚝𝚑𝚛𝚘𝚙𝚒𝚌/𝚌𝚕𝚊𝚞𝚍𝚎-𝚘𝚙𝚞𝚜-𝟺.𝟾'
Vercel Firewall now supports creating custom rules with natural language:
▪︎ Block all /wp-admin requests
▪︎ Rate limit /login to 5 attempts per IP
▪︎ Challenge /checkout requests from node
Vercel Sandbox firewall can now proxy and filter outbound requests.
▪︎ Control all agent traffic from your own proxy
▪︎ More granular credential injection
▪︎ Log and audit outgoing traffic
Superset built a multi-agent IDE that helps build itself.
▪︎ 12 agents running 24/7
▪︎ 1,400 deployments per week
▪︎ 600 preview deployments per day
▪︎ 30-second average build time
Their full AI stack ↓
Introducing 𝚟𝚎𝚛𝚌𝚎𝚕 𝚖𝚎𝚝𝚛𝚒𝚌𝚜: query Observability Plus metrics via the Vercel CLI.
Give your agents access to:
• Query your observability data
• Analyze your app performance
• Debug issues
You can now render @HyperFrames_ on @Vercel
One click gets you a full programmatic video pipeline: live preview, server-side rendering, and MP4 output
All on Vercel infra
Deploy instantly
Build your hyperframes app with vercel 👇
You can now secure native integration resources by restricting where they can be used.
Set marketplace credentials to production-only to protect credentials as sensitive environment variables with MFA controls.