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

capabilities overview

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

Vision models like GPT-4o process both text and images

Vision models such as GPT-4o can process both text and images, enabling multimodal interactions where users can send image URLs along with text prompts.

OpenAI vision models accept image URLs

OpenAI's vision models like GPT-4o can accept multiple image formats via URL in the parts array. Images are sent as file objects with mediaType and url properties.

Vision models enable multimodal interactions

Vision-language models can analyze visual content and text together, enabling applications like visual question answering, image description, and visual detail analysis. This multimodal approach allows asking questions about images and requesting visual analysis.

AI SDK standardizes integrating AI models across supported providers

The AI SDK standardizes integrating artificial intelligence (AI) models across supported providers. This enables developers to focus on building great AI applications, not waste time on technical details.

Generative artificial intelligence definition

Generative artificial intelligence refers to models that predict and generate various types of outputs such as text, images, or audio based on what's statistically likely, pulling from patterns they've learned from their training data. Examples include: generating captions from photos, generating transcriptions from audio files, and generating images from text descriptions.

Large Language Models (LLM) definition

A large language model (LLM) is a subset of generative models focused primarily on text. An LLM takes a sequence of words as input and aims to predict the most likely sequence to follow. It assigns probabilities to potential next sequences and then selects one, continuing to generate sequences until it meets a specified stopping criterion. LLMs learn by training on massive collections of written text.

LLM limitations and hallucination

Large Language Models have limitations. When asked about less known or absent information, like the birthday of a personal relative, LLMs might hallucinate or make up information. It is essential to consider how well-represented the information you need is in the model.

Embedding model definition

An embedding model is used to convert complex data like words or images into a dense vector representation, known as an embedding. Unlike generative models, embedding models do not generate new text or data. Instead, they provide representations of semantic and syntactic relationships between entities that can be used as input for other models or other natural language processing tasks.

AI SDK unified interface for provider abstraction

AI SDK Core offers a standardized approach to interacting with LLMs through a language model specification that abstracts differences between providers. This unified interface allows switching between providers with ease while using the same API for all providers.

Anthropic Claude supports image input and object generation

All Anthropic Claude models listed (claude-sonnet-5, claude-fable-5, claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-sonnet-4-6, claude-opus-4-5, claude-opus-4-1, claude-opus-4-0, claude-sonnet-4-0) support image input, object generation, tool usage, and tool streaming.

OpenAI vision models accept image input

All OpenAI GPT models listed in the capabilities table support image input, including gpt-5.6, gpt-5.5, gpt-5.4-pro, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.3-chat-latest, gpt-5.2-pro, gpt-5.2-chat-latest, gpt-5.2, gpt-5, gpt-5-mini, gpt-5-nano, gpt-5.1-chat-latest, gpt-5.1-codex-mini, gpt-5.1-codex, gpt-5.1, gpt-5-codex, and gpt-5-chat-latest.

Providers supporting PDF chat

PDF-capable providers include Anthropic's Claude 3.7, Google's Gemini 2.5, and OpenAI's GPT-4.1.

PDF file input support across providers

PDF inputs are supported by Anthropic, OpenAI, Google Gemini, and Google Vertex. Only select models within these providers support PDF inputs.

Give your agent this brain