We're excited to introduce the GenAI Gateway Token Quota Policy in Azure API Management, designed to help organizations manage token consumption effectively when experimenting with large language models (LLMs). This new policy allows administrators to set flexible token quotas on a daily, weekly, or monthly basis, giving you control over cumulative usage and helping prevent unexpected costs.
With the GenAI Gateway Token Quota Policy, you can empower developers to innovate freely while maintaining control over consumption and costs, ensuring that your organization's experimentation with LLMs remains both dynamic and cost-effective.