Skip to content
Last updated

Pre-warm the Redis cache for an assistant to reduce latency on the first conversation request.

POSThttps://api.aitronos.com/v1/assistants/{assistant_id}/warm

Pre-warm the Redis cache for an assistant by fetching it from the database and storing the context in Redis. Subsequent conversation requests will skip the database query entirely, saving 10–50ms per request.

The cache TTL is 30 minutes. This is typically called after saving a flow that contains an assistant node.

Path Parameters

assistant_id string required

The unique identifier of the assistant to warm.


Returns

Returns an object containing the assistant ID and current cache status.

cURL
curl -X POST "https://api.aitronos.com/v1/assistants/asst_abc123/warm" \
  -H "X-API-Key: $FREDDY_API_KEY"