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

English

Search in Docs

⌘K

Home

• Home

Speech

• Speech-to-text
• Speech synthesis
• Audio generation
• Speech-to-speech

Alibaba Cloud Model Studio home page

English

Models

Get Started

• Model service overview
• First API call to Qwen
• Recommended models
• Error codes
• Rate limiting
• Regions and service deployment scopes
• Model List

Model Billing

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

Model calls

• Text
• Vision
• Speech
  • Speech-to-text
  • Speech synthesis
  • Audio generation
  • Speech-to-speech
• Embedding
• Omni-modal

Model Inference

• Fast mode (Prime)
• TPM reservation
• Batch inference
• Dedicated Deployment
• Intelligent Routing

Fine-tuning

• Qwen model tuning
• Fine-tune image generation models
• Fine-tuning video generation models

Evaluation

• Model Evaluation (New) for International Site
• Define evaluation dimensions
• Training set and evaluation set

Statistics and Monitoring

• Model usage
• Model monitoring

Security and Compliance

• Permission management
• Transmission security
• Input and output AI guardrail
• 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
• Best practices for high-concurrency speech synthesis
• Third-party model integration tutorial
• Real-time Audio and Video Integration
• Legacy model guides

Support

• FAQ
• Related agreements