This topic introduces the Standard Edition and Professional Edition of RDS Copilot, compares their features, and explains the billing model for the basic plan and AI capacity plan in the Professional Edition.
Standard Edition and Professional Edition
RDS Copilot is available in two editions:
Standard Edition: Supports all features in the RDS Copilot console. Provides AI-driven database diagnostics and query optimization at no cost. Suitable for developers, DBAs, and other technical users who want to improve their productivity.
Professional Edition: Builds on the Standard Edition by adding API access (for integration with internal enterprise platforms), batch instance health checks, ecosystem integrations (such as DingTalk and Lark bots), and dedicated technical support. You can add AI capacity plan to improve O&M efficiency. Suitable for enterprise-grade intelligent database O&M. When you activate the Professional Edition, a basic plan(which includes baseline task concurrency and API call quota) is purchased by default. You can add AI capacity plan on demand to scale capabilities.
Key differences
Item | Standard Edition | Professional Edition |
Cost | Free | When you activate the Professional Edition, a basic plan (USD 869/month) is purchased by default. You can add AI capacity plan on demand. |
Console features | Both editions support all features in the RDS Copilot console. | |
Advanced features | Not supported |
|
Task concurrency | 1 (cannot be scaled) |
|
API access | Not supported |
|
Supported database engines | Both editions support RDS MySQL, PostgreSQL, SQL Server, and MariaDB. | |
Number of managed instances | Unlimited (all instances can use RDS Copilot for intelligent O&M). | |
Use cases | Developers, DBAs, and other technical users who want to improve their productivity. | Intelligent O&M for medium and large enterprises or core business systems, or scenarios where RDS intelligent O&M capabilities need to be integrated into internal enterprise platforms. |
Basic plan and AI capacity plan
When you activate the Professional Edition of RDS Copilot, a basic plan is purchased by default. The basic planprovides baseline task concurrency, intelligent health check capacity, and API call quota. For higher concurrency, faster health checks, or a larger API call quota, add AI capacity plan on top of the basic plan. Each additional AI Capacity Package provides approximately: 10 more concurrent tasks, reduced intelligent health check time, and improved slow query optimization efficiency.
Configuration | Task concurrency | Batch intelligent health check time (100 instances) | API access | Use case |
basic plan(required) | 5 | 60 minutes | Up to 1 billion tokens per day | Try API integration with internal enterprise systems |
basic plan + 1 AI capacity plans | 15 | 20 minutes | Up to 2.7 billion tokens per day | Daily O&M for medium enterprises |
basic plan + 2 AI capacity plans | 25 | 12 minutes | Up to 4.4 billion tokens per day | Batch management for large systems |
basic plan+ 3 AI capacity plans | 35 | 8 minutes | Up to 6.1 billion tokens per day | Frequent health checks for core business |
basic plan + 4 AI capacity plans | 45 | 6 minutes | Up to 7.8 billion tokens per day | Real-time monitoring for finance-grade workloads |
basic plan + 5 AI capacity plans | 55 | 5 minutes | Up to 9.5 billion tokens per day |
Model consumption coefficients
The Professional Edition API supports multiple models, including the Qwen series and embedding/rerank models. Different models consume different amounts of tokens, and the API call quota is deducted based on a consumption coefficient. The coefficient consists of an input token consumption coefficient and an output token consumption coefficient. For example, if the input coefficient of the qwen3.5-plus model is 5.3, each input token deducts 5.3 tokens from the quota. If the output coefficient is 31.8, each output token deducts 31.8 tokens from the quota.
The following table lists the coefficients of commonly used models. For the complete model list and the latest coefficients, see the console.
Model | Input token consumption coefficient | Output token consumption coefficient | Use case |
qwen-flash | 1 | 10 | High-frequency simple queries and fast-response scenarios |
qwen3.5-plus | 5.3 | 31.8 | General dialog and everyday Q&A |
qwen3.6-plus | 13.33 | 80 | Vision understanding, multimodal data analysis, and complex document parsing |
qwen3.7-plus | 13.33 | 53.32 | General dialog, moderate-complexity reasoning, and knowledge Q&A |
qwen3.7-max | 80 | 240 | Top-tier complex reasoning, code generation and optimization, and long-document deep analysis |
qwen3-rerank | 3.33 | N/A | Retrieval result reranking and relevance ranking |
text-embedding-v4 | 3.33 | N/A | Text vectorization, semantic search, and RAG scenarios |
qwen3.5-flash | 1.33 | 13.33 | Lightweight text data generation, high-frequency dialog, and fast summarization |
Billing
When you activate the Professional Edition of RDS Copilot, a basic plan is purchased by default. You can add AI capacity plan on demand:
Basic plan fee: USD 869 per month
AI capacity plan fee: USD 1,448 per package per month (up to 5 AI capacity plan)