Search posts, papers, and topics
30 posts
Vercel now offers Spend Management at no extra cost to Enterprise teams on Flexible Commitment plans. Teams can define per‑cycle budgets that generate alerts, webhooks, or optionally pause production deployments when spend approaches the limit.
Vercel's mcp-handler 2.2.0 adds experimental WebMCP support, letting you expose registered MCP tools to in‑browser agents via a single script tag. The script proxies tool calls back to your MCP server with the signed‑in user’s credentials, so no extra OAuth flow is needed.
v0 now supports installing private npm packages by reading credentials from shared environment variables (NPM_TOKEN or NPM_RC). This lets teams use internal registries without exposing secrets to the runtime.
Vercel reports that the Jev decision model was adopted by 13% of paid teams within its first day, outpacing prior model launches. Jev claims to be up to 194× faster and 445× cheaper than general‑purpose LLMs while returning structured, probabilistic decisions.
Hacktron reported an RCE in libheif, an AVIF decoder used by Next.js image optimization. Vercel and Hacktron reproduced the issue, then coordinated with upstream maintainers (sharp, libvips, libheif) to deploy platform-wide mitigations and release fixes across the ecosystem.
Vercel AI Gateway now offers the GLM‑5.3‑FlashX model, a fast (~200 tps) multimodal coding LLM. The post includes a TypeScript streaming example, notes the model’s fit for coding agents and interactive tools, and lists AI Gateway features (unified API, usage tracking, retries/failover, custom reporting, key budgets, routing rules) with no platform fee.
Vercel CLI 59.16.0 adds sub‑second static artifact deployments by detecting eligible sites and bypassing the build step. Deploy up to 10 HTML/Markdown files (≤5 MB) with a single command and receive a live URL in under a second.
Vercel now lets you enable Turbo build machines on a per‑deployment basis via a commit flag, CLI option, or REST API field, giving temporary extra resources without changing project defaults.
Vercel now supports running Harbor benchmarks, like Terminal‑Bench, inside its Sandbox using Firecracker microVMs. The integration with AI Gateway lets you benchmark multiple models by swapping the `--model` flag, scaling concurrency with `--n-concurrent`.
Vercel’s `skills` CLI (v1.7.0) now lets you install agent skills directly from Notion pages or shared Notion skill packs. Use `npx skills add notion` to browse packs, or `npx skills add <PAGE_URL>` for a single skill. Authentication is handled via the `ntn` CLI, which requires a Notion personal access token. Permissions follow Notion’s page sharing model, so only users with view access can instal…
Vercel’s September AI Gateway Production Index shows open‑weight models processing 56% of token volume (up from 7% in Dec 2025) while accounting for only 14% of spend. Token price fell 23.2% month‑over‑month. Anthropic’s Opus 5 captured 22.5% of spend, overtaking Fable 5 which dropped to 4.9%. OpenAI’s new GPT‑6 Astra grabbed ~7.7% of total gateway spend in its first 12 days, more than double Ant…
Vercel now lets you connect native Marketplace resources to custom environments, not just production, preview, or development. Scope the generated environment variables with the `--environment` flag or equivalent API field, and redeploy to apply.
Vercel AI Gateway now offers OpenAI’s GPT‑Live 1, a full‑duplex voice model that can listen and speak simultaneously. The SDK lets you start a voice session and optionally delegate work to any text model, with code examples for both patterns.
Vercel Hobby projects now retain fewer old deployments to manage the 10GB storage limit. The new policy keeps only the 3 most recent production and 3 most recent overall deployments, with immediate deletion for projects over capacity.
Mem0, a service that provides long‑term memory for AI agents, is now available as a native Vercel Marketplace integration. It auto‑creates an API key, adds it as MEM0_API_KEY, and offers built‑in billing with free and paid plans.
Vercel’s Secure Compute and Static IP builds now start 64% faster by using prewarmed containers, cutting the time from deployment creation to build start from 6.7 s to 2.4 s. The change is automatic and requires no user action.
Is Agentic added a site‑type selector that lets you view audit results in one of four categories—Docs & content, Business, App, or Commerce—by adding a simple meta tag. The underlying score stays unchanged; only the highlighted checks differ, and the tag is optional as the service can infer the type.
Vercel AI Gateway now offers Jev, a probabilistic decision model that returns typed choices, scores, and booleans instead of raw text. TypeSafe AI reports it runs up to 193× faster and 445× cheaper than standard LLMs, exposed via the experimental evaluate API in AI SDK 7.
Delphi migrated its Python backend to Vercel, leveraging Workflows, Queues, and AI Gateway to eliminate infrastructure overhead. The change let a 10‑engineer team ship over 100 production deploys daily with fast onboarding and reliable model routing.
Vercel AI Gateway now offers Google’s Gemini 3.8 Live and Live Extended Thinking models through its realtime WebSocket API, enabling real‑time spoken interactions with audio output and parallel reasoning. The post includes a short TypeScript example for token acquisition, WebSocket setup, and handling of realtime events.
Vercel added full Sandbox egress firewall capabilities to the Hobby plan, letting you define allow/deny network policies and attach secrets to outbound requests. You can configure policies via code or the Sandbox CLI, reducing data exfiltration risk for low‑cost projects.
Vercel Sandbox adds support for Devin Outposts, letting each AI agent session run in an isolated microVM with snapshot state and firewall controls. Teams can deploy via a provided quickstart and get automatic credential handling.
Vercel added full support for Next.js 16.3, bringing leaner prefetching, immutable static assets, and faster route metadata handling. Early adopters see up to 45% fewer prefetches, 24% less static traffic, and roughly 2× faster routing at scale.
Vercel released the @agent-browser/eve extension, giving Eve agents full browser automation capabilities inside their sandbox. It adds installable tools for navigation, interaction, and screenshots, with domain allowlists and credential protection.
Vercel now ships ISR page metadata together with the page files, removing a separate upload step. This reduces deploy times by up to a third for apps that have many ISR or partially prerendered pages, with no extra configuration needed.
Vercel AI Gateway offers DeepSeek v4 Flash at a 90% discount through Novita for Pro customers until Aug 11. Use the `order:['novita']` option to route requests and fall back to other providers if needed.
Vercel has made its Web Application Firewall for Blob storage generally available. It lets you add edge‑evaluated IP, country, and path rules to block or rate‑limit traffic to stored objects without changing code, helping cut unwanted bandwidth and costs.
Factory runs its entire SaaS backend on a single Next.js app deployed to Vercel, handling about a billion API requests per day with 350 ms p95 latency. They achieve this with Vercel’s Fluid compute to avoid cold starts, built‑in observability and WAF for security, and internal automation (“Droids”) that let non‑engineers deploy tools without extra infrastructure.
Vercel added read‑only sharing of Container Registry repositories across teams, allowing any team to pull images from a shared repo. The sharing is managed through the dashboard or Vercel CLI and can be used in Vercel Sandbox with a team‑scoped image reference.
Vercel AI Gateway now offers Qwen 3.8 Max, a 2.4 T‑parameter multimodal LLM with up to 1 M token context. It can be invoked via the standard `streamText` API or through Vercel’s coding agents, with no extra platform fees and full control over usage and security.
