The official inference.sh SDKs for Python and JavaScript/TypeScript.

Installation

1# Installation2pip install inferencesh3 4# With async support5pip install inferencesh[async]

Quick Start

1from inferencesh import inference2 3client = inference(api_key="inf_your_key")4 5# Run an app and wait for result6result = client.run({7    "app": "infsh/flux",8    "input": {"prompt": "A sunset over mountains"}9})10 11print(result["output"])

What's in the SDK?

Running Apps

Execute AI apps on inference.sh infrastructure.

• Running Apps — Basic task execution
• Streaming — Real-time progress updates
• Files — File uploads and downloads

Agent SDK

Build and interact with AI agents programmatically.

• Agent SDK Overview — Introduction
• Template Agents — Use existing agents
• Ad-hoc Agents — Create agents on-the-fly
• Building Tools — Define custom tools

Server Proxy

Protect API keys in frontend applications.

• Server Proxy — Proxy setup for all frameworks
• Vercel Deployment — Deploy with Vercel integration

Building Apps

Create your own apps to run on inference.sh. → See Extending Apps for the app development guide.

Environment Variables

1import os2from inferencesh import inference3 4client = inference(api_key=os.environ["INFERENCE_API_KEY"])

TypeScript Support

The JavaScript SDK includes full TypeScript definitions:

1import type { Task, ApiTaskRequest, InferenceConfig } from '@inferencesh/sdk';

Browser & Node.js

The JavaScript SDK works in both environments:

1// Node.js (CommonJS)2const { inference } = require('@inferencesh/sdk');3 4// ES Modules / TypeScript5import { inference } from '@inferencesh/sdk';6 7// Browser (ESM CDN)8import { inference } from 'https://esm.sh/@inferencesh/sdk';

Note: Never expose API keys in client-side code. Use the Server Proxy in production.

Requirements