MaaS
MaaS
All results for "
" in this service
All results for "
" in this service
What's New
Product Bulletin
MaaS Model Release Notes
MaaS Model Retirement Announcement
Service Overview
What Is MaaS?
Advantages
Use Cases
Core Features
MaaS Concepts
Security
Shared Responsibilities
Asset Identification and Management
Identity Authentication and Access Control
Data Protection
Audit and Logging
Service Resilience
Security Risk Monitoring
Fault Recovery
Update Management
Certificates
Secure Boundaries
Notes and Constraints
Permissions Management
MaaS and Other Services
Quotas
Billing
Billing Items
Billing Items for Real-Time Inference
Prices of Real-Time Inference Model Services
Text Generation Models
Billing for Peak and Off-Peak Hours
About Arrears
Configuring MaaS Access Permissions
Calling Large Model APIs for the First
Model Calling
Recommended Models
Model List
Text Generation
Text Generation Overview
Deep Thinking
Prefix Completion
Function Calling
Image Understanding
ModelArts Studio (MaaS) API Call Specifications
Sending a Chat Request (Chat/Post)
MaaS Standard API V2
MaaS Standard API V1
OpenAI-compatible APIs
Anthropic-compatible APIs
Obtaining the Model List (Models/GET)
Error Codes
Accessing a Client/Development Tool
OpenClaw
OpenCode
Claude Code
Dify
Cherry Studio
Cursor
Cline
Appendix
Managing API Keys
Viewing a Built-in Model in Model Square
Subscribing to Built-in Services
Creating an Endpoint
Model Inference
Preparing MaaS Resources
Creating a Model
Deploying a Model Service
Calling a Model Service
Managing My Services
Starting, Stopping, or Deleting a Service
Scaling Model Service Instances
Modifying the QPS of a Model Service
Upgrading a Model Service
Calling Statistics & Performance Monitoring
Viewing the Call Data and Monitoring Metrics of Real-Time Inference in MaaS
Viewing MaaS Call Data and Monitoring Metrics on Cloud Eye
Best Practices
MaaS Best Practice Overview
Experiencing GLM Models
Experiencing the GLM-5.1 Model
Experiencing DeepSeek Models
Experiencing the DeepSeek-V4-Pro Model
API Reference
Before You Start
API Overview
Calling APIs
Making an API Request
Authentication
Responses
Endpoint
Creating an Endpoint
Editing an Endpoint
Querying Custom Endpoints
Deleting an Endpoint
Enabling or Disabling an Endpoint
Querying ModelArts Real-Time Services
Obtaining Region Information
Obtaining Workspace Information
Obtaining Inference Service Information
Obtaining the Latest Content Guard Disclaimer
MaaS Call Statistics
Obtaining Total Statistics
Obtaining the Service Statistics List
Obtaining Time-based Service Metric Statistics
Obtaining Service Error Details
Obtaining the Service List
Querying the IP Address List
Querying Resource Monitoring Metric Details
Querying the Calling Data of a Service Version
Obtaining the Metrics Supported by Different Model Types
Obtaining Time-based Service Error Code Statistics
Appendixes
Status Codes
Error Codes
Obtaining a Project ID and Name
Obtaining an Account Name and Account ID
Obtaining a Username and ID
FAQs
What Is Token?
How Long Does It Take for an API Key to Become Valid After It Is Created in MaaS?
Can I Use an API Key Across Regions?
What Are the Format Requirements for Configuring the Model Service API URL?
How Do I Obtain the Model Name?
Can I Send 300 Requests per Second If the RPM Value of the Model Service Is 300?
What Should I Do If the Subscription Status is Frozen When I Use a Built-in Service?
Can the Tokens Used by IAM Users Be Billed Separately?
Configuring Missing MaaS Permissions
Videos
General Reference
Glossary
Shared Responsibilities
Service Level Agreement
White Papers
Endpoints
Permissions