diff --git a/deployment/pipecat-cloud/fundamentals/scaling.mdx b/deployment/pipecat-cloud/fundamentals/scaling.mdx index bb974344..86779be9 100644 --- a/deployment/pipecat-cloud/fundamentals/scaling.mdx +++ b/deployment/pipecat-cloud/fundamentals/scaling.mdx @@ -241,13 +241,14 @@ Pipecat Cloud auto-scales your agents. For most cases, the only action you need Pipecat Cloud bills based on: -- Active session minutes -- Reserved session minutes +- **Active session minutes**: Time your agents spend handling live sessions +- **Reserved session minutes**: Time your warm agent instances are kept running, even when idle -An active session starts when you call the `/start` endpoint (or CLI or SDK equivalent). The active session ends when your pipeline shuts down. +An active session starts when you call the `/start` endpoint (or CLI or SDK equivalent) and ends when your agent's pipeline shuts down. -Reserved session minutes are the time your warm agent instances are kept running, even if they are not handling active sessions. When active sessions start, the auto-scaler may provision further warm agent instances to support the next incoming request. Reserved session minutes are optional and controlled by setting `--min-agents` in your deployment configuration. +Reserved session minutes are optional and controlled by setting `--min-agents` in your deployment configuration. - Both active and reserved session minutes are rounded up to the nearest minute. + Both active and reserved session time is measured to the second and billed in + minutes.