Vercel Releases v0 AI Model for Web Application Development, Compatible with OpenAI API

Vercel, the company behind the vibe coding platform for web application development, v0, is now releasing an artificial intelligence (AI) model. Announced on Thursday, the v0 AI model is available via an application programming interface (API), as well as other formats. It is the first AI model developed by the company. The San Francisco-based cloud platform as a service (PaaS) company says the AI model is specialised for web application development (front and back-end) tasks, and is compatible with OpenAI's API.

Vercel's v0 AI Model Can Develop Websites and Web Apps

In a post on X (formerly known as Twitter), the official handle of v0, announced the release of the new AI model. It is the same model that powers the vibe coding platform v0, and the company says it specialises in website development knowledge. It is currently available in beta via the company API, as an AI software development kit (SDK), or via AI Playground.

Vercel says the AI model, officially named v0-1.0-md, supports both text and images as input and is designed to provide responses fast. Additionally, the model is also compatible with the OpenAI Chat Completions API format. It features a context window of up to 1,28,000 tokens, and has a maximum output context size of 32,000 tokens. The model has a limit of a maximum of 200 messages per day.

The v0 AI model can perform framework-aware completions and has been tested on Next.js and Vercel's stack. It can identify and fix bugs, glitches, and other coding errors during generation, as well as add inline edits whenever necessary.

Notably, the v0 API is currently available in beta to developers who have an active Premium or Team subscription with usage-based billing enabled. The AI model costs $3 (roughly Rs. 260) per million input tokens and $15 (roughly Rs. 1,290) per million output tokens.

Vibe coding is quickly becoming a popular way to code among developers. The term refers to describing coding tasks in natural language to AI models, which then do the code writing. This type of coding allows the human operator to take a strategy-driven role, where they give direction to the project, check for errors, and ensure the final vision is achieved.