Ship anything with Vercel

Deploy your first app, set up your coding agent to build and deploy on Vercel, or call any AI model through AI Gateway.

Deploy an app
Set up your agent
Call a model

terminal

npm i -g vercel
vercel login
vercel

terminal

# Plugin for Claude Code, Codex, Grok Build, Cursor, Copilot, Kimi Code
npx plugins add vercel/vercel-plugin

# Skills for any other agent
npx skills add vercel-labs/agent-skills

# Let your agent manage projects, deployments, and logs
npx -y add-mcp https://mcp.vercel.com -g

# Route your agent's model calls through AI Gateway
npx vercel ai-gateway setup

terminal

# Create an API key and export the key it prints
vercel ai-gateway api-keys create
export AI_GATEWAY_API_KEY="your-ai-gateway-api-key"

# Call any model through one endpoint
curl https://ai-gateway.vercel.sh/v1/chat/completions \
  -H "Authorization: Bearer $AI_GATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-5",
    "messages": [{ "role": "user", "content": "Why is the sky blue?" }]
  }'

Set up your coding agent

Set up the agent you code with, and the platform for the agents you ship. This prompt installs the Vercel Plugin or Agent Skills, connects the Vercel MCP server, and deploys your project:

Agent Prompt

Help me set up this project on Vercel. Read https://vercel.com/docs/getting-started-with-vercel first. Then: 1. Install the Vercel CLI globally (npm i -g vercel) and log in with vercel login. 2. If you are Claude Code, OpenAI Codex, Grok Build, Cursor, GitHub Copilot, or Kimi Code, install the Vercel Plugin with npx plugins add vercel/vercel-plugin. Otherwise, install Vercel Skills with npx skills add vercel-labs/agent-skills. 3. Connect the Vercel MCP server with npx -y add-mcp https://mcp.vercel.com -g. 4. Deploy with vercel and share the preview URL. 5. Suggest next steps based on my project, such as adding a custom domain, setting environment variables, or configuring Vercel Functions.

What's new

The latest changes across the Vercel platform. Browse the full changelog for everything that shipped.

• [Sep 25, 2026] Push images to Vercel Container Registry from GitHub Actions. The vercel/vcr-action/login GitHub Action logs workflows into Vercel Container Registry with GitHub OIDC, removing long-lived registry credentials from secrets.
• [Sep 25, 2026] Pixel Canary is now available on Vercel AI Gateway, with strengths in coding, frontend development, and mobile app design.
• [Sep 25, 2026] Vercel Sandbox now supports memory observability. Vercel sandbox memory usage data can now be accessed in the dashboard and CLI.
• [Sep 24, 2026] Vercel Connect now supports TanStack AI. Authenticate TanStack AI MCP clients with Vercel Connect. Tokens are issued at runtime and consent is handled at the route boundary, so nothing is stored in your environment.

Build with AI

• AI Gateway: Call hundreds of models through one endpoint with the AI SDK, any OpenAI-compatible SDK, or cURL, with budgets, fallbacks, and usage monitoring.
• AI SDK: Build chat, agents, and structured output in TypeScript with streaming and tool calling across React, Next.js, Vue, Svelte, and Node.js.
• eve: Deploy and run durable backend AI agents built with eve, an open-source, filesystem-first agent framework.
• Sandbox: Run untrusted or agent-generated code in isolated, ephemeral execution environments.
• Workflows: Build durable, observable applications and AI agents with the Workflow SDK on a fully managed platform.
• MCP Servers: Build and deploy Model Context Protocol servers so agents can call your APIs and systems as tools.

Build your app

Next.js: Deploy Next.js with zero configuration, or bring one of 40+ supported frameworks.
Functions: Run server-side code on demand with Fluid compute, which scales concurrency for AI and I/O-heavy workloads.
Routing Middleware: Run code before a request completes to rewrite, redirect, or personalize responses.
Incremental Static Regeneration: Regenerate static pages on a schedule or on demand without rebuilding your whole site.
Image Optimization: Resize and convert images on demand and serve them from the CDN in modern formats.
Environments: Manage local, preview, production, and custom environments and the variables each one uses.

Secure your app

• Web Application Firewall: Block attacks, scrapers, and unwanted traffic with custom rules, IP blocking, and managed rulesets.
• Bot Management: Detect automated traffic and decide which bots can reach your app.
• BotID: Protect sensitive routes from sophisticated bots with an invisible check instead of a CAPTCHA.
• Deployment Protection: Control who can open your preview and production URLs with Vercel Authentication, passwords, or trusted IPs.

Deploy and operate

• Deploy from Git: Connect GitHub, GitLab, or Bitbucket to deploy on every push, with a preview URL for every branch.
• Domains: Add a custom domain, manage DNS records, and get SSL certificates automatically.
• CDN: Cache responses close to your users and control routing, compression, and revalidation for every deployment.
• Rolling Releases: Send a new deployment to a percentage of traffic first, then promote it or roll back.
• Instant Rollback: Revert production to a previous deployment without a rebuild when something breaks.
• Observability: Monitor traffic, function performance, and errors with framework-aware insights across your apps and AI workflows.

Guides and tutorials

Go deeper with guides, videos, and tutorials from the Vercel Knowledge Base:

• Agent Stack: Build AI agents, integrate language models, and deploy AI-powered apps.
• Backend: Server-side patterns, API routes, database connections, and compute.
• Services: Deploy multiple frontends and backends within a single Vercel project.
• Security: Protect your apps with authentication, firewall rules, and compliance guides.
• Integrations: Connect third-party tools, CMSs, and services to your Vercel project.
• Migrations: Bring your existing apps, agents, and workflows to Vercel.