AWS 推出 Claude Haiku 5.5：面向高吞吐量 Agent 与成本敏感型工作负载

英文标题：Introducing Claude Haiku 5.5 on AWS

Anthropic 的 Claude Haiku 5.5 现已登陆 Amazon Bedrock 和 Claude Platform on AWS，被定位为 Claude 5.5 系列中速度最快、效率最高的模型。AWS 表示，该模型面向子 Agent、高并发及成本敏感型任务，在大多数任务上的成本较 Claude Haiku 4.5 低约 75%。Haiku 5.5 支持编码、工具调用、计算机使用、高分辨率图像和多步骤 Agent 工作流，并首次为 Haiku 系列提供 effort controls。开发者可通过 Amazon Bedrock Playground、InvokeModel、Converse API 或 Anthropic Messages API 调用该模型，并借助 AWS 的身份、审计、监控和计费体系进行生产部署。

1.3 MB 1.3 MB 2.4 KB 345.0 KB 141.2 KB 346.5 KB 202.7 KB 16.4 KB 25.4 KB 25.0 KB 23.6 KB 52.7 KB

import boto3
import json

# Create a Bedrock Runtime client
bedrock_runtime = boto3.client(
    service_name="bedrock-runtime",
    region_name="us-east-1"
)

# Invoke Claude Haiku 5.5
response = bedrock_runtime.invoke_model(
    modelId="global.anthropic.claude-haiku-5-5",
    contentType="application/json",
    accept="application/json",
    body=json.dumps({
        "anthropic_version": "bedrock-2023-05-31",
        "max_tokens": 4096,
        "messages": [
            {
                "role": "user",
                "content": "Can you explain the features of Amazon Bedrock?"
            }
        ]
    })
)

result = json.loads(response["body"].read())
# Haiku 5.5 may return a thinking block before the text block,
# so select the text block rather than a fixed index.
print(next(b["text"] for b in result["content"] if b["type"] == "text"))

import boto3

# Create a Bedrock Runtime client
bedrock_runtime = boto3.client(
    service_name="bedrock-runtime",
    region_name="us-east-1"
)

# Invoke Claude Haiku 5.5
response = bedrock_runtime.converse(
    modelId="global.anthropic.claude-haiku-5-5",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "text": "Can you explain the features of Amazon Bedrock?"
                }
            ]
        }
    ],
    inferenceConfig={
        "maxTokens": 4096
    }
)

if 'output' in response:
    blocks = response['output']['message']['content']
    print('\n'.join(b.get('text', '') for b in blocks if 'text' in b))

from anthropic import Anthropic
from aws_bedrock_token_generator import provide_token

token = provide_token(region="us-east-1")

client = Anthropic(
    base_url="https://bedrock-runtime.us-east-1.amazonaws.com/anthropic",
    api_key=token,
)

# Invoke Claude Haiku 5.5
response = client.messages.create(
    model="global.anthropic.claude-haiku-5-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Can you explain the features of Amazon Bedrock?"}],
)
print(response)

import boto3
import json

# Create a Bedrock Runtime client
bedrock_runtime = boto3.client(
    service_name="bedrock-runtime",
    region_name="us-east-1"
)

# Invoke Claude Haiku 5.5
response = bedrock_runtime.invoke_model(
    modelId="global.anthropic.claude-haiku-5-5",
    contentType="application/json",
    accept="application/json",
    body=json.dumps({
        "anthropic_version": "bedrock-2023-05-31",
        "max_tokens": 4096,
        "messages": [
            {
                "role": "user",
                "content": "Can you explain the features of Amazon Bedrock?"
            }
        ]
    })
)

result = json.loads(response["body"].read())
# Haiku 5.5 may return a thinking block before the text block,
# so select the text block rather than a fixed index.
print(next(b["text"] for b in result["content"] if b["type"] == "text"))

import boto3

# Create a Bedrock Runtime client
bedrock_runtime = boto3.client(
    service_name="bedrock-runtime",
    region_name="us-east-1"
)

# Invoke Claude Haiku 5.5
response = bedrock_runtime.converse(
    modelId="global.anthropic.claude-haiku-5-5",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "text": "Can you explain the features of Amazon Bedrock?"
                }
            ]
        }
    ],
    inferenceConfig={
        "maxTokens": 4096
    }
)

if 'output' in response:
    blocks = response['output']['message']['content']
    print('\n'.join(b.get('text', '') for b in blocks if 'text' in b))

from anthropic import Anthropic
from aws_bedrock_token_generator import provide_token

token = provide_token(region="us-east-1")

client = Anthropic(
    base_url="https://bedrock-runtime.us-east-1.amazonaws.com/anthropic",
    api_key=token,
)

# Invoke Claude Haiku 5.5
response = client.messages.create(
    model="global.anthropic.claude-haiku-5-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Can you explain the features of Amazon Bedrock?"}],
)
print(response)