@kmskrishna
Yes, on the Pay-As-You-Go plan, the concurrency limit is normally 10 concurrent calls. However, when you switch to an Enterprise plan, we reserve GPUs for you on our Enterprise cluster, which allows you to scale up to millions of concurrent calls. The exact concurrency limit on the Enterprise plan can be tailored to your specific needs, ensuring guaranteed low latency and the ability to handle a very high volume of calls. Would you like to know more about the Enterprise plan or how to upgrade?