Agent API Considerations (Pilot)

Review these considerations before you use the Agent API.

Each call to the Agent API consumes Einstein Requests. The number of Einstein Requests used depends on the API call size and the large language model (LLM) usage type multiplier. To learn more, see Generative AI Billable Usage Types and the Rate Card for Einstein Requests. Agent API isn’t subject to conversation-based billing.

The Agent API has a 120-second timeout. When a call times out, you receive an HTTP 500 response.