Gradio

What it does

Gradio takes ordinary Python code, such as a machine learning model, an API call or any function, and produces a browser-based interface around it. You choose input and output components (text boxes, images, audio, video, 3D, dataframes, plots, chat), and Gradio generates the page. It also exposes each app so it can be queried programmatically from Python or JavaScript.

People use it to prototype and demo models without writing JavaScript or CSS. A few lines using gr.Interface wrap a function, gr.ChatInterface builds a chatbot UI, and gr.Blocks allows custom layouts and multi-step data flows. Setting share=True creates a public link while the model keeps running on your own machine, and apps can be hosted on Hugging Face Spaces. Hot reload mode speeds up local development, and apps can be served as MCP servers.

It suits Python developers, data scientists and researchers who need a shareable interface for a model or tool. It is a code library, so you must be comfortable writing Python, and Python 3.10 or higher is required. The library is free under Apache 2.0, but compute is yours unless you host elsewhere. Highly bespoke front-end design needs Blocks, custom components or the server mode.

What it can do

• Wrap any Python function in a web UI with gr.Interface
• Build chatbot interfaces with gr.ChatInterface
• Design custom layouts and event flows with gr.Blocks
• 40+ input/output components for images, audio, video, 3D and dataframes
• Public share links via launch(share=True)
• Python and JavaScript clients to query apps programmatically

Works with

• Hugging Face Spaces
• MCP

Example workflows

Demo a model to colleagues

Input: a Python function wrapping a trained model. Steps: define gr.Interface with matching input and output components, run python app.py, then launch with share=True. Output: a public URL where others try the model in a browser while computation stays on your machine.

Build a chatbot UI

Input: a Python function that returns replies to messages. Steps: pass it to gr.ChatInterface, run with the gradio command for hot reload while editing, then deploy to Hugging Face Spaces. Output: a working chat web app.

Before you choose

• Share links serve the app from your own computer, so it must stay running for others to use it.
• Heavily customised interfaces require learning gr.Blocks or custom components rather than the simple Interface class.

Listed under

• Coding
• Demos
• Developers
• Machine learning
• Prototyping
• Python
• Web apps

Get started

Then write a few lines of Python and run the file.

1. Install Python 3.10 or higher, ideally in a virtual environment.
2. Run pip install --upgrade gradio.
3. Write app.py using gr.Interface, then run python app.py or gradio app.py and open localhost:7860.

The source code is available under Apache 2.0. Local compute and optional paid hosting are separate; Spaces also offers free CPU hosting.

Source: github.com/gradio-app/gradio, checked 28 Oct 2026. Prices can change; check before you buy.

Sources for this overview

Product pages, documentation, and pricing checked 28 Oct 2026. Each source supports part of the overview; availability and prices can change.

• Gradio ↗gradio.app
• GitHub - gradio-app/gradio: Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work! · GitHub ↗github.com
• Quickstart ↗gradio.app

Company website

gradio.app: product, pricing and policy pages

YC directory mirror

Batch and company name

Web search

Confirms the official site

Social accounts

Accounts the company links, and its posts on X

Human review

Checked by a person

knowledge_base

Last checked 28 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.