Vercel releases its first model for building web applications

1 week ago 6

The v0-1.0-md model is designed for building modern web applications. It supports text and image inputs, provides fast streaming responses, and is compatible with the OpenAI Chat Completions API format.

Framework aware completions: Evaluated on modern stacks like Next.js and Vercel.
Auto-fix: Identifies and corrects common coding issues during generation.
Quick edit: Streams inline edits as they’re available.
OpenAI compatible: Can be used with any tool or SDK that supports OpenAI's API format.
Multimodal: Supports both text and image inputs (base64-encoded image data).

You can experiment with the v0-1.0-md model in the AI Playground to test prompts and view responses.

The v0 API is currently in beta and requires a Premium or Team plan with usage-based billing enabled. For details, visit the pricing page.

To start using the v0-1.0-md model, create an API key on v0.dev.

You can then integrate it using the AI SDK, a TypeScript library designed for working with v0 and other OpenAI-compatible models.

npm install ai @ai-sdk/vercel

import { generateText } from 'ai'; import { vercel } from '@ai-sdk/vercel'; const { text } = await generateText({ model: vercel('v0-1.0-md'), prompt: 'Create a Next.js AI chatbot with authentication', });

The v0-1.0-md model is the default model served by the v0 API.

Capabilities:

Supports text and image inputs (multimodal)
Compatible with OpenAI’s Chat Completions format
Supports function/tool calls
Streaming responses with low latency
Optimized for frontend and full-stack web development

POST https://api.v0.dev/v1/chat/completions

This endpoint generates a model response based on a list of messages.

HeaderRequiredDescription

Authorization	Yes	Bearer token: Bearer $V0_API_KEY
Content-Type	Yes	Must be application/json

FieldTypeRequiredDescription

model	string	Yes	Model name. Use "v0-1.0-md".
messages	array	Yes	List of message objects forming the conversation.
stream	boolean	No	If true, the response will be returned as a stream of data chunks.
tools	array	No	Optional tool definitions (e.g., functions or API calls).
tool_choice	string or object	No	Specifies which tool to call, if tools are provided.

Each message object must contain:

FieldTypeRequiredDescription

role	string	Yes	One of "user", "assistant", or "system".
content	string or array	Yes	The message content. Can be a string or array of text/image blocks.

curl https://api.v0.dev/v1/chat/completions \ -H "Authorization: Bearer $V0_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "v0-1.0-md", "messages": [ { "role": "user", "content": "Create a Next.js AI chatbot" } ] }'

curl https://api.v0.dev/v1/chat/completions \ -H "Authorization: Bearer $V0_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "v0-1.0-md", "stream": true, "messages": [ { "role": "user", "content": "Add login to my Next.js app" } ] }'

If stream is false (default), the response is a JSON object:

{ "id": "v0-123", "model": "v0-1.0-md", "object": "chat.completion", "created": 1715620000, "choices": [ { "index": 0, "message": { "role": "assistant", "content": "Here's how to add login to your Next.js app..." }, "finish_reason": "stop" } ] }

If stream is true, the server returns a series of data chunks formatted as Server-Sent Events (SSE). Each line begins with data: followed by a partial delta:

{ "id": "v0-123", "model": "v0-1.0-md", "object": "chat.completion.chunk", "choices": [ { "delta": { "role": "assistant", "content": "Here's how" }, "index": 0, "finish_reason": null } ] }

LimitValue