Methods: AIStats#createBatch(...), AIStats#retrieveBatch(...), AIStats#cancelBatch(...), AIStats#getAsyncJobWebSocketUrl(...), AIStats#getBatchWebSocketUrl(...), client.asyncJobs.websocketUrl(...)
import ai.stats.sdk.AIStats;
import java.util.HashMap;
import java.util.Map;
AIStats client = new AIStats(apiKey, "https://api.phaseo.app/v1");
Map<String, Object> request = new HashMap<>();
request.put("endpoint", "responses");
request.put("input_file_id", "file_123");
request.put("completion_window", "24h");
request.put("session_id", "agent-run-42");
Object created = client.createBatch(request);
Object retrieved = client.retrieveBatch("batch_123");
Object cancelling = client.cancelBatch("batch_123");
String websocketUrl = client.getBatchWebSocketUrl("batch_123", 1500, null);
System.out.println(String.valueOf(created));
System.out.println(String.valueOf(retrieved));
System.out.println(String.valueOf(cancelling));
System.out.println(websocketUrl);
Key parameters
endpoint (required): Target endpoint for batch items such as responses.input_file_id (required): File id uploaded through the files API.completion_window: Upstream batch completion window such as 24h.session_id: Optional AI Stats grouping id for logs, sessions, and investigate tooling.webhook: Optional webhook configuration for async lifecycle notifications.metadata: Optional object persisted with the batch.
Batch responses also surface gateway observability fields such as request_id, provider, echoed session_id / webhook, and terminal billing / pricing_lines when available.
Use client.getBatchWebSocketUrl(...) when you want to subscribe to the documented /v1/async/batch/{id}/ws lifecycle stream instead of polling only.
Use client.asyncJobs.websocketUrl("batch", batchId, ...) when you want the generic async-jobs resource helper.
Use client.getAsyncJobWebSocketUrl("batch", batchId, ...) when you want the same generic helper without going through the resource object. Last modified on May 6, 2026
