Scale and Performance

Contextual allows you to choose from 5 different Agent sizes that have different CPU and memory allocations to match to the precise needs of your AI-solution logic.

If you're running a low use HTTP endpoint that might be fine on a small agent. If you're running a machine learning model it might require an XL.

Additionally, on paid plans you can set scaling for your agents to create multiple instances to handle more load. Scaling can happen through either CPU-based utilization (for HTTP or Event-Based Agents) or Message Lag (for Event-Based Agents only).

Per-hour pricing and detailed metrics for agents are available on our pricing page.