The v0 API Is GA: Vercel Just Made Its App-Building Agent a Headless Service

On August 5, Vercel made the v0 API generally available: programmatic, headless access to the agent behind v0.app. Send a prompt, and v0 generates an app, starts a dev server in a Vercel Sandbox, and hands you a preview URL you can embed in your own UI. One API call goes from prompt to a running application, and a second call deploys it.

The announcement, dated August 5, is short on positioning and long on mechanics, which is appropriate: the interesting part is not that an API exists, it is what the API models. This is not a "generate a code snippet" endpoint. It is a stateful agent that reads, edits, and runs files in an isolated workspace, streams its trace back to you, and verifies its own work against a running dev server.

What shipped#

The new surface is a v2 API (https://api.v0.dev/v2) plus an SDK in the v0 npm package:

• Chats hold app state - each chat is one app in one workspace, and follow-up messages iterate on it; chats.createFromRepo starts from a GitHub repository, a ZIP archive, or a set of files.
• Sync, async, and streaming modes - chats.create blocks for the completed response, createAsync returns IDs for polling or webhooks, and createStream emits ordered message parts (text, thinking, file edits, bash commands, tool calls) as the agent works. Usage is returned with chat and message responses so you can meter the work.
• Previews and deploys - each chat gets a short-lived preview token that you fetch from a server route and proxy, so your API key never reaches the client; chats.createVercelProject wires the chat to a Vercel project and chats.deploy ships it.

The agent-native part#

The v0 API was clearly designed to be called by other agents, not just by humans in a UI. An MCP server at https://v0.app/api/mcp (OAuth on first connection) exposes chat, task, and preview-URL tools to any MCP-capable client; @v0-sdk/ai-tools turns the same operations into AI SDK tools for TypeScript agents; and Vercel's eve agents attach it via an OpenAPI connection file, with the API key applied at execution time, out of model context. Each request can also carry up to three skills - from team or user memory, skills.sh, or the connected repo - and Design Systems 2.0 saves a design system as a skill, the first real mechanism for keeping generated apps on your design language at scale.

For existing users the v1-to-v2 migration is breaking: v1 chats do not run on v2, the chat now holds app state while messages hold history, and clients must render message parts rather than only final text.

What it costs#

The announcement says nothing about price, and as of 2026-08-13 neither the API docs nor the v2 reference publishes an API-specific price list or a rate limit - that is the honest gap in an otherwise mechanics-heavy launch. What Vercel does publish is the shared credit system the product runs on. Per the v0 plans page, generations draw from your credit balance: Free is $0/month with $5 of included monthly credits and a 7-message daily limit; Plus is $30/user/month and Business is $100/user/month, each with $30 of included monthly credits per user plus $2 of free daily credits on login, with Business adding training opt-out by default and Enterprise custom-priced. Unused monthly credits expire after 65 days; purchased credits expire one year after purchase.

Credits convert to work at per-model token rates on the v0 pricing page (vendor-published, as of 2026-08-13): v0 Mini at $0.20/$1.20 per 1M input/output tokens, v0 Pro at $2/$10, v0 Max at $5/$25, and v0 Max Fast at $10/$50, each with cache write/read rates alongside. The usage object returned on chat and message responses is what you reconcile against those rates. The missing piece is any documented API request ceiling, so until Vercel publishes one, capacity planning for a production integration is a conversation with them rather than a number in the docs.

Why it matters#

Vercel has been assembling an agent platform for a year: eve for agents, Sandbox for isolated runtimes, AI Gateway for model routing, and now a headless v0. The pattern across all of them is the same, and our interaction models post called the shape of it: the unit of value is shifting from a generated snippet to a running, verified, deployable artifact.

The v0 API makes that artifact addressable by software. A white-labeled app builder, an automated change pipeline triggered from CI or a webhook, and an agent that hands back a working app instead of a code block are the three use cases Vercel names, and all three share one property: they treat v0 as a component in a larger system rather than a destination. That is the architectural line between v0 the product and v0 the platform.

Two honest caveats. First, this is a managed agent service: the workspace, the dev server, and the verification loop all run on Vercel's infra, which is the tradeoff for zero setup but also the lock-in to price. Second, preview tokens are short-lived by design, so any production embedding needs the proxy pattern from the docs; that is a server-side integration, not a copy-paste iframe.

For teams already running agent pipelines, this is the first mainstream app-builder API that ships with a streaming trace, metered usage, and a deployment path as first-class primitives rather than afterthoughts. If you are building agent loops, that is the detail worth studying.

Continue Reading#

• Vercel eve: The Framework for Building AI Agents - where agents live in Vercel's platform, and how eve connections attach tools and keys
• Build Your First Agent with Vercel eve: A Step-by-Step Tutorial - a hands-on walkthrough of the eve stack
• Interaction Models for AI Developer Tools - the design patterns behind snippet, agent, and platform-shaped tools
• The MCP Server Ecosystem: A Developer's Guide - how MCP servers like the new v0 one plug into IDEs and runtimes
• Everything Vercel Shipped at Ship 26 - the wider Vercel agent platform context
• Chat SDK Adds Durable Approvals: Agent Workflows That Wait For a Human - related deep dive

Sources#

• Introducing the new v0 API - Vercel Blog, fetched August 5, 2026
• v0 API Overview - v0.app Docs, fetched August 5, 2026
• v0 API Migration Guide (v1 to v2)
• v0 Plans and Pricing - v0.app Docs, fetched August 13, 2026
• v0 Pricing (model token rates), fetched August 13, 2026