experimental_getBatchStatus

Retrieves the latest status of an asynchronous batch. For a complete guide to the batch lifecycle, see Batch.

import { anthropic } from '@ai-sdk/anthropic';
import { experimental_getBatchStatus as getBatchStatus } from 'ai';

const status = await getBatchStatus({
  provider: anthropic,
  batch,
});

console.log(status.status, status.requestCounts);

Import

import { experimental_getBatchStatus } from "ai"

API Signature

Parameters

• provider? (Experimental_BatchProvider): The provider used to access the batch. Defaults to the global provider, or the AI Gateway when no global provider is configured.
• batch (Experimental_BatchReference): The serializable reference returned by experimental_startBatch.
• providerOptions? (ProviderOptions): Additional provider-specific options for status retrieval.
• maxRetries? (number): Maximum number of retries for status retrieval. Set to 0 to disable retries. Default: 2.
• abortSignal? (AbortSignal): An optional abort signal to cancel the request.
• timeout? (number | { totalMs?: number }): Maximum time allowed for the status request.
• headers? (Record<string, string | undefined>): Additional HTTP headers for the request.

Returns

• status ('pending' | 'completed' | 'failed'): The latest normalized batch status.
• rawStatus? (string): The provider-specific batch status, when available.
• requestCounts? ({ total: number; pending: number; completed: number; failed: number }): Provider-reported request counts.
• error? (Experimental_BatchError): Error details when the batch fails.
• createdAt? (string): Creation timestamp, when provided by the provider.
• expiresAt? (string): Expiration timestamp, when provided by the provider.
• providerMetadata? (ProviderMetadata): Provider-specific metadata for the batch.