# What is Keras? Definition and meaning

A simple API for defining and training neural networks across several backends.

## Definition

**Keras**: A simple API for defining and training neural networks across several backends.

In short: High-level deep-learning API.

## When it is used

Rapid model prototyping.

## Where it fits

Keras belongs to **Frameworks** in the [Deep learning](/topics/deep-learning) topic. These are the other terms in the same group:

- **[PyTorch](/glossary/pytorch)**: A flexible framework with dynamic computation graphs and strong GPU support.
- **[PyTorch Lightning](/glossary/pytorch-lightning)**: A library that organizes training loops, distributed training and logging.
- **[TensorFlow](/glossary/tensorflow)**: An end-to-end platform with a graph runtime and deployment tooling.
- **[JAX](/glossary/jax)**: A library for array computing with automatic differentiation, JIT compilation and easy parallelism on accelerators.
- **[Hugging Face](/glossary/hugging-face)**: A platform and set of libraries for models, datasets and training tools such as Transformers.

## Learn more

The full guide to **[Keras](/tools/keras)** explains how it works, when to use it and how it compares with the alternatives, with examples. The [glossary](/glossary) lists every term on the site from A to Z.

Previous term: [Kafka Connect](/glossary/kafka-connect) · Next term: [Kimi K3](/glossary/kimi-k3)
