Documentation Index
Fetch the complete documentation index at: https://mulerouter.ai/docs/llms.txt
Use this file to discover all available pages before exploring further.
Overview
MuleRouter CLI is the official command-line interface for MuleRouter. It exposes every supported text-to-image, text-to-video, image-to-video, text-to-speech, and text-to-music endpoint through a single, scriptable binary calledmulerouter.
The CLI is designed for three audiences:
- Developers who want to try a model without writing any integration code.
- Operators and scripts that need to drive generation from shell pipelines, cron jobs, or CI.
- AI agents that can shell out to a stable, JSON-aware command.
Highlights
- 40+ model endpoints across Alibaba, Google, KlingAI, Midjourney, OpenAI and more.
- One verb per task:
list,params,run,status,config. - Async-aware: every long-running task can either be polled to completion or queued with
--no-waitand resumed later viastatus. - Local file support: pass
--image /path/to/photo.pngand the CLI validates, reads, and base64-encodes the file automatically. - JSON mode on every command for clean machine-readable output.
- Zero runtime config beyond an API key — the binary talks to
https://api.mulerouter.aiout of the box.
Packages
The CLI ships as two npm packages that you can mix and match:| Package | What it is | When to install |
|---|---|---|
mulerouter | The mulerouter executable | You want the CLI |
@mulerouter/core | The TypeScript SDK that powers the CLI — registry, API client, task poller, image helpers | You are embedding MuleRouter calls in a Node/Bun/TypeScript program |
picocolors (used only by the CLI for terminal colors).
Where to go next
Install & configure
Install the binary and point it at your API key.
Quickstart
Generate your first image, video, or audio clip in under a minute.
Commands
Reference for every subcommand and flag.
Model cheatsheet
Pick the right endpoint for the job.