new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

vercel/models

5 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Vercel model v0-1.5-md

The v0-1.5-md model is designed for everyday tasks and UI generation. It supports text and image inputs, function/tool calls, streaming responses with low latency, and is optimized for frontend and full-stack web development.

Vercel model v0-1.5-lg

The v0-1.5-lg model is designed for advanced thinking or reasoning. It supports text and image inputs, function/tool calls, streaming responses with low latency, and is optimized for frontend and full-stack web development.

Vercel model v0-1.0-md legacy

The v0-1.0-md model is the legacy model served by the v0 API. It supports text and image inputs, function/tool calls, streaming responses with low latency, and is optimized for frontend and full-stack web development.

Vercel model usage with generateText

Models can be created using a provider instance and called with generateText function. Example: const { text } = await generateText({ model: vercel('v0-1.5-md'), prompt: 'Create a Next.js AI chatbot' });

Vercel models support streamText function

Vercel language models can also be used with the streamText function from the AI SDK Core.

Give your agent this brain