BCM

• Automatic Activation: Baidu Cloud Monitor does not necessitate any additional purchases or activations. The service is automatically activated when users register for a Baidu AI Cloud account. After purchasing and using Baidu AI Cloud products, users can view the product's operational status and set up alarms through the Baidu Cloud Monitor management console. Currently, BCM automatically monitors 60+ Baidu AI Cloud products. (New APM application performance monitoring and LLM application performance monitoring modules should be enabled separately)
• Timely and Accurate Alarms: When status changes of the monitor object trigger alarm, the system provides notifications via email, SMS, phone calls, webhooks, etc., enabling users to promptly stay informed about application operations.
• Intuitive Data Display: Dashboard provides rich visualization forms to meet personalized monitoring and analysis needs. It supports comparative analysis of multiple instances and metrics, meeting visualization needs for monitor data across various scenarios.
• Batch Alarms for Instance: Users can directly add alarms for instances or add alarms in batch via instance groups or tags, significantly improving the work efficiency of operation personnel.

APM Application Performance Monitor

• Easy to use: After activation, applications can be quickly onboarded following the access process, gaining out-of-the-box observability capabilities
• Multi-language support: Supports major programming languages such as Java, Go, and Python.
• Embrace open source ecosystem: Support the industry-standard OpenTelemetry
• Comprehensive features: Provide application topology, Trace Explorer, API analysis, SQL analysis, exception analysis, log analysis and other comprehensive application performance monitor capabilities to help you quickly locate online performance issues

LLM Application Performance Monitor

• Easy to use: After activation, applications can be quickly onboarded following the access process, gaining out-of-the-box LLM application observability capabilities.
• Embrace open source: Support the industry-standard OpenTelemetry and various LLM frameworks and components.
• Metric visualization: Provide model call analysis and token analysis capabilities, statistically analyze key metrics of LLM application calls at a global level to make technology-to-service enablement outcomes "visible".
• Process transparency: Customize domain-specific trace semantics for LLM applications, reveal internal operations from user-level I/O to parameter details of each span, thus enabling "white-box" visibility for each call.