Install the belt CLI skill: npx skills add belt-sh/cli
Run AI apps in the cloud with a simple CLI. No GPU required.
Install CLI
curl -fsSL https://cli.inference.sh | sh
belt login
Agents / non-interactive shells: printf %s "$KEY" | belt login --key-stdin, or set INFERENCE_API_KEY (read on every command, no login needed; older belt versions read INFSH_API_KEY, now deprecated).
Without a TTY, belt login prints a URL; the browser then shows a claim code. Run belt login --code <code> on the same machine within 5 minutes.
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):
# 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
Quick Examples
# Generate an image
belt app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut"}'
# Generate a video
belt app run google/veo-3-1-fast --input '{"prompt": "drone over mountains"}'
# Call Claude
belt app run openrouter/claude-sonnet-45 --input '{"prompt": "Explain quantum computing"}'
# Web search
belt app run tavily/search-assistant --input '{"query": "latest AI news"}'
# Post to Twitter
belt app run x/post-create --input '{"text": "Hello from AI!"}'
# Generate 3D model
belt app run infsh/rodin-3d-generator --input '{"prompt": "a wooden chair"}'
Local File Uploads
The CLI automatically uploads local files when you provide a path instead of a URL:
# Upscale a local image
belt app run falai/topaz-image-upscaler --input '{"image": "/path/to/photo.jpg", "upscale_factor": 2}'
# Image-to-video from local file
belt app run falai/wan-2-5-i2v --input '{"image": "./my-image.png", "prompt": "make it move"}'
# Avatar with local audio and image
belt app run bytedance/omnihuman-1-5 --input '{"audio": "/path/to/speech.mp3", "image": "/path/to/face.jpg"}'
# Post tweet with local media
belt app run x/post-create --input '{"text": "Check this out!", "media": ["./screenshot.png"]}'
Commands
| Task |
Command |
| Browse the app store |
belt app list |
| Search apps |
belt app search "flux" |
| Filter by category |
belt app list --category image |
| Get app details |
belt app get google/veo-3-1-fast |
| Generate sample input |
belt app sample google/veo-3-1-fast --save input.json |
| Run app |
belt app run google/veo-3-1-fast --input input.json |
| Run without waiting |
belt app run <app> --input input.json --no-wait |
| Check task status |
belt task get <task-id> |
What's Available
| 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, MMAudio |
| 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-create, dm-send, user-follow, post-like, post-retweet |
| Utilities |
Media merger, caption videos, image stitching, audio extraction |
Related Skills
# Image generation (FLUX, Gemini, Grok, Seedream)
npx skills add inference-sh/skills@ai-image-generation
# Video generation (Veo, Seedance, Wan, OmniHuman)
npx skills add inference-sh/skills@ai-video-generation
# LLMs (Claude, Gemini, Kimi, GLM via OpenRouter)
npx skills add inference-sh/skills@llm-models
# Web search (Tavily, Exa)
npx skills add inference-sh/skills@web-search
# AI avatars & lipsync (OmniHuman, Fabric, PixVerse)
npx skills add inference-sh/skills@ai-avatar-video
# Twitter/X automation
npx skills add inference-sh/skills@twitter-automation
# Model-specific
npx skills add inference-sh/skills@flux-image
npx skills add inference-sh/skills@google-veo
# Utilities
npx skills add inference-sh/skills@image-upscaling
npx skills add inference-sh/skills@background-removal
Reference Files
- Authentication & Setup
- Discovering Apps
- Running Apps
- CLI Reference
Documentation
1---2name: agent-tools-23description: "Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok"4allowed-tools: Bash(belt *)5metadata:6 source: https://skillmd.com/skills/inference-sh/agent-tools-27---89> **Install the belt CLI skill:** `npx skills add belt-sh/cli`1011# [inference.sh](https://inference.sh)1213Run AI apps in the cloud with a simple CLI. No GPU required.1415](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kgjw8atdxgkrsr8a2t5peq7b.jpeg)1617## Install CLI1819```bash20curl -fsSL https://cli.inference.sh | sh21belt login22```2324Agents / non-interactive shells: `printf %s "$KEY" | belt login --key-stdin`, or set `INFERENCE_API_KEY` (read on every command, no login needed; older belt versions read `INFSH_API_KEY`, now deprecated).25Without a TTY, `belt login` prints a URL; the browser then shows a claim code. Run `belt login --code <code>` on the same machine within 5 minutes.2627> **What does the installer do?** The [install script](https://cli.inference.sh) 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](https://docs.sigstore.dev/cosign/system_config/installation/) installed, the installer also verifies the Sigstore signature automatically.28>29> **Manual install** (if you prefer not to pipe to sh):30> ```bash31> # Download the binary and checksums32> curl -LO https://dist.inference.sh/cli/checksums.txt33> 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)34> # Verify checksum35> sha256sum -c checksums.txt --ignore-missing36> # Extract and install37> tar -xzf inferencesh-cli-*.tar.gz38> mv inferencesh-cli-* ~/.local/bin/inferencesh39> ```4041## Quick Examples4243```bash44# Generate an image45belt app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut"}'4647# Generate a video48belt app run google/veo-3-1-fast --input '{"prompt": "drone over mountains"}'4950# Call Claude51belt app run openrouter/claude-sonnet-45 --input '{"prompt": "Explain quantum computing"}'5253# Web search54belt app run tavily/search-assistant --input '{"query": "latest AI news"}'5556# Post to Twitter57belt app run x/post-create --input '{"text": "Hello from AI!"}'5859# Generate 3D model60belt app run infsh/rodin-3d-generator --input '{"prompt": "a wooden chair"}'61```6263## Local File Uploads6465The CLI automatically uploads local files when you provide a path instead of a URL:6667```bash68# Upscale a local image69belt app run falai/topaz-image-upscaler --input '{"image": "/path/to/photo.jpg", "upscale_factor": 2}'7071# Image-to-video from local file72belt app run falai/wan-2-5-i2v --input '{"image": "./my-image.png", "prompt": "make it move"}'7374# Avatar with local audio and image75belt app run bytedance/omnihuman-1-5 --input '{"audio": "/path/to/speech.mp3", "image": "/path/to/face.jpg"}'7677# Post tweet with local media78belt app run x/post-create --input '{"text": "Check this out!", "media": ["./screenshot.png"]}'79```8081## Commands8283| Task | Command |84|------|---------|85| Browse the app store | `belt app list` |86| Search apps | `belt app search "flux"` |87| Filter by category | `belt app list --category image` |88| Get app details | `belt app get google/veo-3-1-fast` |89| Generate sample input | `belt app sample google/veo-3-1-fast --save input.json` |90| Run app | `belt app run google/veo-3-1-fast --input input.json` |91| Run without waiting | `belt app run <app> --input input.json --no-wait` |92| Check task status | `belt task get <task-id>` |9394## What's Available9596| Category | Examples |97|----------|----------|98| **Image** | FLUX, Gemini 3 Pro, Grok Imagine, Seedream 4.5, Reve, Topaz Upscaler |99| **Video** | Veo 3.1, Seedance 1.5, Wan 2.5, OmniHuman, Fabric, MMAudio |100| **LLMs** | Claude Opus/Sonnet/Haiku, Gemini 3 Pro, Kimi K2, GLM-4, any OpenRouter model |101| **Search** | Tavily Search, Tavily Extract, Exa Search, Exa Answer, Exa Extract |102| **3D** | Rodin 3D Generator |103| **Twitter/X** | post-create, dm-send, user-follow, post-like, post-retweet |104| **Utilities** | Media merger, caption videos, image stitching, audio extraction |105106## Related Skills107108```bash109# Image generation (FLUX, Gemini, Grok, Seedream)110npx skills add inference-sh/skills@ai-image-generation111112# Video generation (Veo, Seedance, Wan, OmniHuman)113npx skills add inference-sh/skills@ai-video-generation114115# LLMs (Claude, Gemini, Kimi, GLM via OpenRouter)116npx skills add inference-sh/skills@llm-models117118# Web search (Tavily, Exa)119npx skills add inference-sh/skills@web-search120121# AI avatars & lipsync (OmniHuman, Fabric, PixVerse)122npx skills add inference-sh/skills@ai-avatar-video123124# Twitter/X automation125npx skills add inference-sh/skills@twitter-automation126127# Model-specific128npx skills add inference-sh/skills@flux-image129npx skills add inference-sh/skills@google-veo130131# Utilities132npx skills add inference-sh/skills@image-upscaling133npx skills add inference-sh/skills@background-removal134```135136## Reference Files137138- [Authentication & Setup](references/authentication.md)139- [Discovering Apps](references/app-discovery.md)140- [Running Apps](references/running-apps.md)141- [CLI Reference](references/cli-reference.md)142143## Documentation144145- [Agent Skills Overview](https://inference.sh/blog/skills/skills-overview) - The open standard for AI capabilities146- [Getting Started](https://inference.sh/docs/getting-started/introduction) - Introduction to inference.sh147- [What is inference.sh?](https://inference.sh/docs/getting-started/what-is-inference) - Platform overview148- [Apps Overview](https://inference.sh/docs/apps/overview) - Understanding the app ecosystem149- [CLI Setup](https://inference.sh/docs/extend/cli-setup) - Installing the CLI150- [Workflows vs Agents](https://inference.sh/blog/concepts/workflows-vs-agents) - When to use each151- [Why Agent Runtimes Matter](https://inference.sh/blog/agent-runtime/why-runtimes-matter) - Runtime benefits152