跳轉到主要內容

​
概覽

LemonData 支援原生的 Anthropic Messages API 格式。請搭配 LemonData 使用官方 Anthropic SDK 來存取 Claude 模型。

​
安裝

pip install anthropic

​
配置

from anthropic import Anthropic

client = Anthropic(
    api_key="sk-your-lemondata-key",
    base_url="https://api.lemondata.cc"
)
注意：Anthropic SDK 的 base URL 為 https://api.lemondata.cc（不含 /v1）。

​
基本用法

message = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello, Claude!"}
    ]
)

print(message.content[0].text)

​
使用 System Prompt

message = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    system="You are a helpful coding assistant.",
    messages=[
        {"role": "user", "content": "Write a Python function to reverse a string"}
    ]
)

​
串流 (Streaming)

with client.messages.stream(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Tell me a story"}]
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

​
視覺 (Vision)

import base64

# From URL
message = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What's in this image?"},
            {
                "type": "image",
                "source": {
                    "type": "url",
                    "url": "https://example.com/image.jpg"
                }
            }
        ]
    }]
)

# From base64
with open("image.png", "rb") as f:
    image_data = base64.b64encode(f.read()).decode()

message = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Describe this image"},
            {
                "type": "image",
                "source": {
                    "type": "base64",
                    "media_type": "image/png",
                    "data": image_data
                }
            }
        ]
    }]
)

​
工具使用 (Tool Use)

message = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=1024,
    tools=[{
        "name": "get_weather",
        "description": "Get the weather for a location",
        "input_schema": {
            "type": "object",
            "properties": {
                "location": {"type": "string", "description": "City name"}
            },
            "required": ["location"]
        }
    }],
    messages=[{"role": "user", "content": "What's the weather in Tokyo?"}]
)

# Check for tool use
for block in message.content:
    if block.type == "tool_use":
        print(f"Tool: {block.name}")
        print(f"Input: {block.input}")

​
延伸思考 (Extended Thinking) (Claude Opus 4.5)

適用於支援延伸思考的模型： 
message = client.messages.create(
    model="claude-opus-4-5",
    max_tokens=16000,
    thinking={
        "type": "enabled",
        "budget_tokens": 10000
    },
    messages=[{"role": "user", "content": "Solve this complex math problem..."}]
)

# Access thinking blocks
for block in message.content:
    if block.type == "thinking":
        print(f"Thinking: {block.thinking}")
    elif block.type == "text":
        print(f"Response: {block.text}")

​
可用的 Claude 模型

模型最適合
claude-opus-4-5複雜推理、延伸思考
claude-sonnet-4-5通用用途、程式編寫
claude-haiku-4-5快速回應

​
錯誤處理

from anthropic import APIError, APIStatusError, APIConnectionError

try:
    message = client.messages.create(
        model="claude-sonnet-4-5",
        max_tokens=1024,
        messages=[{"role": "user", "content": "Hello"}]
    )
except APIStatusError as e:
    if e.status_code == 401:
        print("Invalid API key")
    elif e.status_code == 429:
        print("Rate limit exceeded")
    else:
        print(f"API error: {e.status_code}")
except APIConnectionError:
    print("Connection error")
except APIError as e:
    print(f"Unexpected error: {e}")

​
比較：OpenAI SDK vs Anthropic SDK

兩者皆可搭配 LemonData 用於 Claude 模型：
特性OpenAI SDKAnthropic SDK
Base URLhttps://api.lemondata.cc/v1https://api.lemondata.cc
Endpoint/chat/completions/v1/messages
System prompt在 messages 陣列中獨立的 system 參數
延伸思考 (Extended thinking)不支援支援
請根據您的偏好或現有的程式碼庫進行選擇。