Message Batches API 支持与 Messages API 相同的功能集。虽然本页面专注于如何使用 Message Batches API，但请参阅 Messages API 示例 了解 Messages API 功能集的示例。

​
创建 Message Batch

import anthropic
from anthropic.types.message_create_params import MessageCreateParamsNonStreaming
from anthropic.types.messages.batch_create_params import Request

client = anthropic.Anthropic()

message_batch = client.messages.batches.create(
    requests=[
        Request(
            custom_id="my-first-request",
            params=MessageCreateParamsNonStreaming(
                model="claude-opus-4-20250514",
                max_tokens=1024,
                messages=[{
                    "role": "user",
                    "content": "Hello, world",
                }]
            )
        ),
        Request(
            custom_id="my-second-request",
            params=MessageCreateParamsNonStreaming(
                model="claude-opus-4-20250514",
                max_tokens=1024,
                messages=[{
                    "role": "user",
                    "content": "Hi again, friend",
                }]
            )
        )
    ]
)
print(message_batch)
JSON
{
  "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF",
  "type": "message_batch",
  "processing_status": "in_progress",
  "request_counts": {
    "processing": 2,
    "succeeded": 0,
    "errored": 0,
    "canceled": 0,
    "expired": 0
  },
  "ended_at": null,
  "created_at": "2024-09-24T18:37:24.100435Z",
  "expires_at": "2024-09-25T18:37:24.100435Z",
  "cancel_initiated_at": null,
  "results_url": null
}

​
轮询 Message Batch 完成状态

要轮询 Message Batch，您需要其 id，该 ID 在创建请求时的响应中提供，或通过列出批次获得。示例 id：msgbatch_013Zva2CMHLNnXjNJJKqJ2EF。

import anthropic

client = anthropic.Anthropic()

message_batch = None
while True:
    message_batch = client.messages.batches.retrieve(
        MESSAGE_BATCH_ID
    )
    if message_batch.processing_status == "ended":
        break
              
    print(f"Batch {MESSAGE_BATCH_ID} is still processing...")
    time.sleep(60)
print(message_batch)

​
列出工作区中的所有 Message Batches

import anthropic

client = anthropic.Anthropic()

# Automatically fetches more pages as needed.
for message_batch in client.messages.batches.list(
    limit=20
):
    print(message_batch)
Output
{
  "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF",
  "type": "message_batch",
  ...
}
{
  "id": "msgbatch_01HkcTjaV5uDC8jWR4ZsDV8d",
  "type": "message_batch",
  ...
}

​
检索 Message Batch 结果

一旦您的 Message Batch 状态为 ended，您将能够查看批次的 results_url 并以 .jsonl 文件的形式检索结果。

import anthropic

client = anthropic.Anthropic()

# Stream results file in memory-efficient chunks, processing one at a time
for result in client.messages.batches.results(
    MESSAGE_BATCH_ID,
):
    print(result)
Output
{
  "id": "my-second-request",
  "result": {
    "type": "succeeded",
    "message": {
      "id": "msg_018gCsTGsXkYJVqYPxTgDHBU",
      "type": "message",
      ...
    }
  }
}
{
  "custom_id": "my-first-request",
  "result": {
    "type": "succeeded",
    "message": {
      "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
      "type": "message",
      ...
    }
  }
}

​
取消 Message Batch

取消后立即，批次的 processing_status 将为 canceling。您可以使用相同的轮询批次完成技术来轮询取消何时最终完成，因为已取消的批次也会以 ended 状态结束，并可能包含结果。

import anthropic

client = anthropic.Anthropic()

message_batch = client.messages.batches.cancel(
    MESSAGE_BATCH_ID,
)
print(message_batch)
JSON
{
  "id": "msgbatch_013Zva2CMHLNnXjNJJKqJ2EF",
  "type": "message_batch",
  "processing_status": "canceling",
  "request_counts": {
    "processing": 2,
    "succeeded": 0,
    "errored": 0,
    "canceled": 0,
    "expired": 0
  },
  "ended_at": null,
  "created_at": "2024-09-24T18:37:24.100435Z",
  "expires_at": "2024-09-25T18:37:24.100435Z",
  "cancel_initiated_at": "2024-09-24T18:39:03.114875Z",
  "results_url": null
}