inference.sh

Run 250+ AI apps in the cloud with a simple CLI. No GPU required.

通过简洁的CLI在云端运行250+款AI应用，无需GPU。

Install CLI

安装CLI

bash

curl -fsSL https://cli.inference.sh | sh
infsh login

What does the installer do? The install script detects your OS and architecture, downloads the correct binary from
dist.inference.sh
, verifies its SHA-256 checksum, and places it in your PATH. That's it — no elevated permissions, no background processes, no telemetry. If you have cosign installed, the installer also verifies the Sigstore signature automatically.
Manual install (if you prefer not to pipe to sh):
bash
# Download the binary and checksums
curl -LO https://dist.inference.sh/cli/checksums.txt
curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep $(uname -s | tr A-Z a-z)-$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/') | head -1 | cut -d'"' -f4)
# Verify checksum
sha256sum -c checksums.txt --ignore-missing
# Extract and install
tar -xzf inferencesh-cli-*.tar.gz
mv inferencesh-cli-* ~/.local/bin/inferencesh

bash

curl -fsSL https://cli.inference.sh | sh
infsh login

安装脚本会做什么？ 安装脚本会检测你的操作系统和架构，从
dist.inference.sh
下载对应的二进制文件，验证其SHA-256校验和，并将其放入你的PATH中。仅此而已——无需提升权限，无后台进程，无遥测数据。如果你已安装cosign，安装脚本还会自动验证Sigstore签名。
手动安装（若你不喜欢通过管道执行sh脚本）：
bash
# 下载二进制文件和校验和
curl -LO https://dist.inference.sh/cli/checksums.txt
curl -LO $(curl -fsSL https://dist.inference.sh/cli/manifest.json | grep -o '"url":"[^"]*"' | grep $(uname -s | tr A-Z a-z)-$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/') | head -1 | cut -d'"' -f4)
# 验证校验和
sha256sum -c checksums.txt --ignore-missing
# 解压并安装
tar -xzf inferencesh-cli-*.tar.gz
mv inferencesh-cli-* ~/.local/bin/inferencesh

Quick Examples

快速示例

bash

undefined

bash

undefined

Generate an image

生成图像

infsh app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut"}'

Generate a video

生成视频

infsh app run google/veo-3-1-fast --input '{"prompt": "drone over mountains"}'

Call Claude

调用Claude

infsh app run openrouter/claude-sonnet-45 --input '{"prompt": "Explain quantum computing"}'

Web search

网页搜索

infsh app run tavily/search-assistant --input '{"query": "latest AI news"}'

Post to Twitter

发布Twitter内容

infsh app run x/post-tweet --input '{"text": "Hello from AI!"}'

Generate 3D model

生成3D模型

infsh app run infsh/rodin-3d-generator --input '{"prompt": "a wooden chair"}'

undefined

infsh app run infsh/rodin-3d-generator --input '{"prompt": "a wooden chair"}'

undefined

Local File Uploads

本地文件上传

The CLI automatically uploads local files when you provide a path instead of a URL:

bash

undefined

当你提供本地文件路径而非URL时，CLI会自动上传该文件：

bash

undefined

Upscale a local image

放大本地图像

infsh app run falai/topaz-image-upscaler --input '{"image": "/path/to/photo.jpg", "upscale_factor": 2}'

Image-to-video from local file

基于本地图片生成视频

infsh app run falai/wan-2-5-i2v --input '{"image": "./my-image.png", "prompt": "make it move"}'

Avatar with local audio and image

基于本地音频和图片生成虚拟形象

infsh app run bytedance/omnihuman-1-5 --input '{"audio": "/path/to/speech.mp3", "image": "/path/to/face.jpg"}'

Post tweet with local media

发布带本地媒体的Twitter内容

infsh app run x/post-create --input '{"text": "Check this out!", "media": "./screenshot.png"}'

undefined

infsh app run x/post-create --input '{"text": "Check this out!", "media": "./screenshot.png"}'

undefined

Commands

命令

Task	Command
List all apps	`infsh app list`
Search apps	`infsh app list --search "flux"`
Filter by category	`infsh app list --category image`
Get app details	`infsh app get google/veo-3-1-fast`
Generate sample input	`infsh app sample google/veo-3-1-fast --save input.json`
Run app	`infsh app run google/veo-3-1-fast --input input.json`
Run without waiting	`infsh app run <app> --input input.json --no-wait`
Check task status	`infsh task get <task-id>`

任务	命令
列出所有应用	`infsh app list`
搜索应用	`infsh app list --search "flux"`
按分类筛选	`infsh app list --category image`
获取应用详情	`infsh app get google/veo-3-1-fast`
生成示例输入	`infsh app sample google/veo-3-1-fast --save input.json`
运行应用	`infsh app run google/veo-3-1-fast --input input.json`
异步运行应用	`infsh app run <app> --input input.json --no-wait`
查看任务状态	`infsh task get <task-id>`

What's Available

可用功能分类

Category	Examples
Image	FLUX, Gemini 3 Pro, Grok Imagine, Seedream 4.5, Reve, Topaz Upscaler
Video	Veo 3.1, Seedance 1.5, Wan 2.5, OmniHuman, Fabric, HunyuanVideo Foley
LLMs	Claude Opus/Sonnet/Haiku, Gemini 3 Pro, Kimi K2, GLM-4, any OpenRouter model
Search	Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract
3D	Rodin 3D Generator
Twitter/X	post-tweet, post-create, dm-send, user-follow, post-like, post-retweet
Utilities	Media merger, caption videos, image stitching, audio extraction

分类	示例
图像类	FLUX、Gemini 3 Pro、Grok Imagine、Seedream 4.5、Reve、Topaz Upscaler
视频类	Veo 3.1、Seedance 1.5、Wan 2.5、OmniHuman、Fabric、HunyuanVideo Foley
大语言模型（LLMs）	Claude Opus/Sonnet/Haiku、Gemini 3 Pro、Kimi K2、GLM-4、所有OpenRouter模型
搜索类	Tavily Search、Tavily Extract、Exa Search、Exa Answer、Exa Extract
3D类	Rodin 3D Generator
Twitter/X自动化	post-tweet、post-create、dm-send、user-follow、post-like、post-retweet
工具类	媒体合并、视频加字幕、图像拼接、音频提取

Related Skills

Image generation (FLUX, Gemini, Grok, Seedream)

图像生成（FLUX、Gemini、Grok、Seedream）

npx skills add inference-sh/skills@ai-image-generation

Video generation (Veo, Seedance, Wan, OmniHuman)

视频生成（Veo、Seedance、Wan、OmniHuman）

npx skills add inference-sh/skills@ai-video-generation

LLMs (Claude, Gemini, Kimi, GLM via OpenRouter)

大语言模型（通过OpenRouter调用Claude、Gemini、Kimi、GLM）

npx skills add inference-sh/skills@llm-models

Web search (Tavily, Exa)

网页搜索（Tavily、Exa）

npx skills add inference-sh/skills@web-search

AI avatars & lipsync (OmniHuman, Fabric, PixVerse)

AI虚拟形象与唇同步（OmniHuman、Fabric、PixVerse）

npx skills add inference-sh/skills@ai-avatar-video

Twitter/X automation

Twitter/X自动化

npx skills add inference-sh/skills@twitter-automation

Model-specific

特定模型技能

npx skills add inference-sh/skills@flux-image npx skills add inference-sh/skills@google-veo

Utilities

工具类技能

npx skills add inference-sh/skills@image-upscaling npx skills add inference-sh/skills@background-removal

undefined

npx skills add inference-sh/skills@image-upscaling npx skills add inference-sh/skills@background-removal

undefined

Reference Files

参考文档

Authentication & Setup
Discovering Apps
Running Apps
CLI Reference

认证与设置
应用发现
运行应用
CLI参考

Documentation

官方文档

Agent Skills Overview - The open standard for AI capabilities
Getting Started - Introduction to inference.sh
What is inference.sh? - Platform overview
Apps Overview - Understanding the app ecosystem
CLI Setup - Installing the CLI
Workflows vs Agents - When to use each
Why Agent Runtimes Matter - Runtime benefits

Agent技能概述 - AI能力开放标准
快速开始 - inference.sh入门指南
什么是inference.sh？ - 平台概览
应用生态概览 - 了解应用生态系统
CLI设置 - CLI安装教程
工作流vs Agent - 适用场景对比
Agent运行时的重要性 - 运行时优势介绍

agent-tools

Original

Translation

inference.sh

inference.sh

Install CLI

安装CLI

Quick Examples

快速示例

Generate an image

生成图像

Generate a video

生成视频

Call Claude

调用Claude

Web search

网页搜索

Post to Twitter

发布Twitter内容

Generate 3D model

生成3D模型

Local File Uploads

本地文件上传

Upscale a local image

放大本地图像

Image-to-video from local file

基于本地图片生成视频

Avatar with local audio and image

基于本地音频和图片生成虚拟形象

Post tweet with local media

发布带本地媒体的Twitter内容

Commands

命令

What's Available

可用功能分类

Related Skills

相关技能

Image generation (FLUX, Gemini, Grok, Seedream)

图像生成（FLUX、Gemini、Grok、Seedream）

Video generation (Veo, Seedance, Wan, OmniHuman)

视频生成（Veo、Seedance、Wan、OmniHuman）

LLMs (Claude, Gemini, Kimi, GLM via OpenRouter)

大语言模型（通过OpenRouter调用Claude、Gemini、Kimi、GLM）

Web search (Tavily, Exa)

网页搜索（Tavily、Exa）

AI avatars & lipsync (OmniHuman, Fabric, PixVerse)

AI虚拟形象与唇同步（OmniHuman、Fabric、PixVerse）

Twitter/X automation

Twitter/X自动化

Model-specific

特定模型技能

Utilities

工具类技能

Reference Files

参考文档

Documentation

官方文档