OpenAIModels

The Audio object provides access to preconfigured audio-enabled Large Language Models (LLMs). These models support both audio input and output functionalities, making them suitable for various audio-centric applications.

Object that provides pre-configured instances of advanced GPT models for different use cases. These instances represent versatile and high-performance large language models capable of handling various tasks like text completion, image input processing, structured outputs, and interfacing with tools.

The CostOptimized object provides a collection of cost-efficient language models optimized for specific use cases. These models aim to balance quality, performance, and affordability, catering to various tasks like reasoning, speculation, and tools integration.

Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.

Object containing moderation models designed to detect harmful content in text and images. These models are free to use and can identify various categories of potentially harmful content.

Object containing a set of pre-configured reasoning models with various capabilities and constraints. These models are designed for tasks ranging from general reasoning to domain-specific applications, supporting key features like multi-step problem solving, structured outputs, and context-based responses.