Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.

Skip to main content

Alibaba Cloud Model Studio home page

Home

User Guide (Models)User Guide (Agent)API Reference (Models)API Reference (Agent)CLI

Get Started

Product introduction
First API call to Qwen
Recommended models
Dynamic rate limiting
Rate limiting
Base URL overview
Regions and endpoints

Billing

Free quota for new users
Model inference pricing
Training and deployment pricing
Savings plans
Billing and cost management
Budget management

Token Plan

Token Plan overview

Model Playground

Audio generation
Music generation

Clients and Developer Tools

OpenClaw
Hermes Agent
Claude Code
OpenCode
Cursor
Codex
Qwen Code
DeepSeek Harness
WorkBuddy
QwenPaw
Cherry Studio
Chatbox
Cline
Qoder
Qoder CN (formerly Lingma)
Kilo CLI
Postman
Dify
More tools

Model Inference

Fast mode (Prime)
TPM reservation
Batch inference
Model Routing

Fine-tuning

Fine-tune image generation models
Fine-tuning video generation models

Evaluation

Model Evaluation (New) for International Site

Statistics and Monitoring

Model usage
Model monitoring

Asset Center

Asset center

Security and Compliance

Permission management
Security certifications and privacy
Training data summary
Data retention policy

Best Practices

Text-to-text prompt guide
Text-to-image prompt guide
wan3.0 Video Generation Prompt Guide
Video generation prompt guide
Best practices for handling rate limiting
Explicit Cache Best Practices

Support

FAQ
Related agreements

Changelog

Model decommissioning policy
Model lifecycle and updates
Model Platform Feature Update Announcements

Deployment Modes

Overview of Model Studio deployment modes: PTU, dedicated compute, Token.

Model Studio offers multiple deployment modes for different performance and cost needs.

PTU Provisioned Throughput deployment
Dedicated compute deployment
Token pay-as-you-go deployment

Previous

What is Alibaba Cloud Model Studio

Alibaba Cloud Model Studio is a one-stop model service platform. It provides the full Qwen series and mainstream third-party LLMs through official Qwen APIs and OpenAI-compatible APIs, with multimodal support across text, image, and audio/video. Call models on demand — no infrastructure to manage.

Alibaba Cloud Model Studio home page

Get Started

Product introduction
First API call to Qwen
Recommended models
Dynamic rate limiting
Rate limiting
Base URL overview
Regions and endpoints

Billing

Free quota for new users
Model inference pricing
Training and deployment pricing
Savings plans
Billing and cost management
Budget management

Token Plan

Token Plan overview

Model Playground

Audio generation
Music generation

Clients and Developer Tools

OpenClaw
Hermes Agent
Claude Code
OpenCode
Cursor
Codex
Qwen Code
DeepSeek Harness
WorkBuddy
QwenPaw
Cherry Studio
Chatbox
Cline
Qoder
Qoder CN (formerly Lingma)
Kilo CLI
Postman
Dify
More tools

Model Inference

Fast mode (Prime)
TPM reservation
Batch inference
Model Routing

Fine-tuning

Fine-tune image generation models
Fine-tuning video generation models

Evaluation

Model Evaluation (New) for International Site

Statistics and Monitoring

Model usage
Model monitoring

Asset Center

Asset center

Security and Compliance

Permission management
Security certifications and privacy
Training data summary
Data retention policy

Best Practices

Text-to-text prompt guide
Text-to-image prompt guide
wan3.0 Video Generation Prompt Guide
Video generation prompt guide
Best practices for handling rate limiting
Explicit Cache Best Practices

Support

FAQ
Related agreements

Changelog

Model decommissioning policy
Model lifecycle and updates
Model Platform Feature Update Announcements