The Vercel v0 API provides large language models, 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. It is optimized for frontend and full-stack web development code generation.

For more details, refer to the official Vercel v0 API documentation.

Authentication

Set your V0_API_KEY environment variable. You can create an API key on v0.dev.

export V0_API_KEY=your-v0-api-key

Example

Use v0 with your Agent. The following example assumes you have the v0 Python class (as you provided) located at agno/models/vercel.py.

from agno.agent import Agent
from agno.models.vercel import v0

agent = Agent(
    model=v0(id="v0-1.0-md"),
    markdown=True
)

# Print the response in the terminal
agent.print_response("Create a simple web app that displays a random number between 1 and 100.")

# agent.print_response("Create a webapp to fetch the weather of a city and display humidity, temperature, and wind speed in cards, use shadcn components and tailwind css")
View more examples here.

Params

ParameterTypeDefaultDescription
idstr"v0-1.0-md"The specific model ID used for generating responses.
namestr"v0"The name identifier for the v0 agent.
providerstr"Vercel"The provider of the model, combining "v0" with the model ID.
api_keyOptional[str]-The API key for authenticating requests to the v0 service. Retrieved from the environment variable V0_API_KEY.
base_urlstr"https://api.v0.dev/v1/"The base URL for making API requests to the v0 service.

v0 also supports the params of OpenAI.