Skip to main content

Documentation Index

Fetch the complete documentation index at: https://platform.minimax.io/docs/llms.txt

Use this file to discover all available pages before exploring further.

For Token Plan users, no coding is required to unlock MiniMax multimodal capabilities in your AI agent: video generation, speech synthesis, music creation, coding, and more. You can call these capabilities directly in assistants like OpenClaw and Claude Code. If you still prefer direct API integration, see the API Documentation.

​
Install and configure the CLI

Copy the prompt below to your AI agent (OpenClaw, Claude Code, Cursor, MaxClaw, AutoClaw, KimiClaw, TRAE, OpenCode, etc.). It will guide you through installing the CLI, signing in, and adding the SKILL:
Please integrate MiniMax CLI (https://github.com/MiniMax-AI/cli) for me in three steps:

1. Install globally: run `npm install -g mmx-cli`, then verify with `mmx --version`
2. Sign in: run `mmx auth login --api-key sk-xxxxx` (replace sk-xxxxx with my actual key); the latest CLI auto-detects the service region from the API Key — if API calls return 401 later, fall back to `mmx config set --key region --value global|cn` to set it manually
3. Install the official SKILL (recommended, helps you call mmx more accurately afterwards): run `npx skills add MiniMax-AI/cli -y -g`

After that, run `mmx quota` to confirm my Token Plan balance.

​
Use the CLI

TextUse minimax to write a 4-line poem about AI
VideoGenerate a video: at sunset, a cat sits by the window looking into the distance
MusicGenerate an upbeat jazz song about a summer beach
SpeechRead in a gentle female voice: Welcome to MiniMax Token Plan. After subscribing, your AI agent can generate video, music, speech, and images with full multimodal capability.
ImageGenerate a cyberpunk city night scene in 16:9Generated files are saved in minimax-output/ under your current directory. If you’re using an agent, it’s recommended to have it display the generated media directly in its output.

​
CLI Dashboard

Run mmx in your terminal to open the CLI panel and quickly discover the main commands, flags, and usage info.

MMX-CLI panel overview
  • resources: available resource types
  • flags: supported options for commands
  • usage: remaining quota and usage overview
  • help: entry points for documentation

​
Capability overview

MMX-CLI provides a single command-line entry point across text, image, video, speech, music, vision understanding, and web search:
CapabilityBasic commandDescription
Textmmx text chatmulti-turn chat, streaming output, system prompts, JSON output
Imagemmx image generatetext-to-image, aspect ratio controls, batch generation
Videommx video generateasync generation, task status, downloading
Speechmmx speech synthesizetext-to-speech (TTS), multiple voices, streaming
Musicmmx music generatetext-to-music, with-lyrics and instrumental modes
Visionmmx vision describeimage understanding from local files, URLs, or file IDs
Searchmmx search querybuilt-in web search
CommandPurposeTypical example
mmx auth status / refresh / logoutShow login identity / refresh credentials / log outmmx auth status
mmx config show / setView or change configuration (region, default model, etc.)mmx config set --key region --value global
mmx quotaView Token Plan usage and remaining quotammx quota
mmx update / mmx update latestCheck for updates / upgrade to the latest versionmmx update latest

​
Usage by modality

For modality-specific Token Plan quotas, see: Token Plan Pricing

​
FAQ

​
Where do I get an API Key?

​
Still getting 401 after login?

mmx auth login usually auto-detects the service region from the API Key. If you still get 401, region detection likely failed — set it manually: 
mmx config set --key region --value global    # Overseas plan
mmx config set --key region --value cn        # Mainland China plan
Then run mmx auth status to confirm the active region matches the platform you purchased from.