Claude Platform Docs

批次

建立訊息批次
$ ant messages:batches create
POST/v1/messages/batches

傳送一批訊息建立請求。

擷取訊息批次
$ ant messages:batches retrieve
GET/v1/messages/batches/{message_batch_id}

此端點具冪等性,可用於輪詢訊息批次是否完成。若要存取訊息批次的結果,請對回應中的 results_url 欄位發出請求。

列出訊息批次
$ ant messages:batches list
GET/v1/messages/batches

列出工作區內的所有訊息批次。最近建立的批次會優先傳回。

取消訊息批次
$ ant messages:batches cancel
POST/v1/messages/batches/{message_batch_id}/cancel

批次可在處理結束前隨時取消。一旦啟動取消,批次便會進入 canceling 狀態,此時系統可能會先完成任何進行中且不可中斷的請求,然後才完成取消。

刪除訊息批次
$ ant messages:batches delete
DELETE/v1/messages/batches/{message_batch_id}

刪除訊息批次。

擷取訊息批次結果
$ ant messages:batches results
GET/v1/messages/batches/{message_batch_id}/results

以 .jsonl 檔案的形式串流傳輸訊息批次的結果。

Models
deleted_message_batch: object{ type: "message_batch_deleted", id }
type: "message_batch_deleted"

Deleted object type.

For Message Batches, this is always "message_batch_deleted".

id: string

ID of the Message Batch.

message_batch: object{ type: "message_batch", id, archived_at, 7 more }
message_batch_canceled_result: object{ type: "canceled" }
type: "canceled"
message_batch_errored_result: object{ type: "errored", error }
message_batch_expired_result: object{ type: "expired" }
type: "expired"
message_batch_individual_response: object{ custom_id, result }

This is a single line in the response .jsonl file and does not represent the response as a whole.

message_batch_request_counts: object{ canceled, errored, expired, 2 more }
canceled: number

Number of requests in the Message Batch that have been canceled.

This is zero until processing of the entire Message Batch has ended.

errored: number

Number of requests in the Message Batch that encountered an error.

This is zero until processing of the entire Message Batch has ended.

expired: number

Number of requests in the Message Batch that have expired.

This is zero until processing of the entire Message Batch has ended.

processing: number

Number of requests in the Message Batch that are processing.

succeeded: number

Number of requests in the Message Batch that have completed successfully.

This is zero until processing of the entire Message Batch has ended.

Processing result for this request.

Contains a Message output if processing was successful, an error response if processing failed, or the reason why processing was not attempted, such as cancellation or expiration.

message_batch_succeeded_result: object{ type: "succeeded", message }