Cloud Model Routing (CMR) is a unified large model gateway service provided by Tencent Cloud for enterprise-grade AI applications. CMR supports unified client access via standard-compatible APIs and manages various large model services across public clouds, third-party providers, and privatized deployments. Enterprises do not need to adapt to protocols and configure keys separately for each model vendor. By configuring access to CMR, they can access model resources from multiple providers and gain unified authentication, quota management, auditing, and observability capabilities.
This document describes the concepts, application scenarios, and billing overview of CMR to help you understand CMR.
This document describes the basic concepts, core capabilities, and working principles of CMR to help you quickly understand and efficiently use CMR.
This document describes the diverse business scenarios of CMR, such as intelligent distribution, access acceleration, and observability and governance.
This document describes the billable items, billing modes, and purchase methods of CMR to help you quickly understand the cost components of CMR.
This document describes how to configure and use CMR, helping you get started quickly.
This document describes how to create a CMR instance and select appropriate configurations based on your business scenario.
This document describes how to create a CMR access key, which you can use to obtain identity credentials for model scheduling.
This document describes how to complete model association and scheduling on a CMR instance.
You can explore CMR best practices to help you use the service more efficiently.
This document walks you through quickly creating an ALB instance and forwarding client requests to backend target groups.
This document covers frequently asked questions you may encounter during configuration.
Was this page helpful?
You can also Contact sales or Submit a Ticket for help.
Help us improve! Rate your documentation experience in 5 mins.
Feedback