Claude Platform Docs

Lots

Créer un lot de messages
POST/v1/messages/batches

Envoyez un lot de requêtes de création de messages.

Récupérer un lot de messages
GET/v1/messages/batches/{message_batch_id}

Ce point de terminaison est idempotent et peut être utilisé pour interroger l'état d'achèvement d'un lot de messages. Pour accéder aux résultats d'un lot de messages, effectuez une requête vers l'URL indiquée dans le champ results_url de la réponse.

Lister les lots de messages
GET/v1/messages/batches

Lister tous les lots de messages d'un espace de travail. Les lots créés le plus récemment sont renvoyés en premier.

Annuler un lot de messages
POST/v1/messages/batches/{message_batch_id}/cancel

Les lots peuvent être annulés à tout moment avant la fin du traitement. Une fois l'annulation lancée, le lot passe à l'état canceling, pendant lequel le système peut terminer les requêtes en cours non interruptibles avant de finaliser l'annulation.

Supprimer un lot de messages
DELETE/v1/messages/batches/{message_batch_id}
Récupérer les résultats d'un lot de messages
GET/v1/messages/batches/{message_batch_id}/results

Diffuse en streaming les résultats d'un lot de messages sous forme de fichier .jsonl.

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

Deleted object type.

For Message Batches, this is always "message_batch_deleted".

defaultmessage_batch_deleted
id: string

ID of the Message Batch.

MessageBatch object{ type: "message_batch", id, archived_at, 7 more }
MessageBatchCanceledResult object{ type: "canceled" }
type: "canceled"
defaultcanceled
MessageBatchErroredResult object{ type: "errored", error }
type: "errored"
defaulterrored
error: ErrorResponse { type: "error", error, request_id }
type: "error"
defaulterror
error: ErrorObject
One of the following:
request_id: string or null
MessageBatchExpiredResult object{ type: "expired" }
type: "expired"
defaultexpired
MessageBatchIndividualResponse object{ custom_id, result }

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

custom_id: string

Developer-provided ID created for each request in a Message Batch. Useful for matching results to requests, as results may be given out of request order.

Must be unique for each request within the Message Batch.

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.

One of the following:
MessageBatchRequestCounts 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.

default0
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.

default0
expired: number

Number of requests in the Message Batch that have expired.

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

default0
processing: number

Number of requests in the Message Batch that are processing.

default0
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.

default0

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.

One of the following:
MessageBatchSucceededResult object{ type: "succeeded", message }
type: "succeeded"
defaultsucceeded
message: Message { type: "message", id, container, 8 more }