原生 SDK
Anthropic SDK
使用 TokenLab 搭配 Anthropic SDK，以相容於 Claude 原生 Messages API
概覽
TokenLab 支援原生 Anthropic Messages API 路徑，因此你可以直接使用官方 Anthropic SDK 來存取 Claude 模型。
對於 Anthropic SDK，請使用 https://api.tokenlab.sh 作為 base URL，且不要自行附加 /v1。
類型: 原生 SDK
主要路徑: Anthropic-native
支援級別: 強原生路徑
在已文件化的 SDK 路徑中，這是對 Claude 原生功能支援最強的一條。
安裝
pip install anthropic設定 Client
from anthropic import Anthropic
client = Anthropic(
api_key="sk-your-tokenlab-key",
base_url="https://api.tokenlab.sh",
)基本用法
message = client.messages.create(
model="claude-sonnet-5",
max_tokens=1024,
messages=[
{"role": "user", "content": "Reply with: Connected to TokenLab."}
]
)
print(message.content[0].text)串流
with client.messages.stream(
model="claude-sonnet-5",
max_tokens=1024,
messages=[{"role": "user", "content": "Write a short poem about coding."}]
) as stream:
for text in stream.text_stream:
print(text, end="", flush=True)視覺
import base64
message = client.messages.create(
model="claude-sonnet-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"
}
}
]
}]
)
with open("image.png", "rb") as f:
image_data = base64.b64encode(f.read()).decode()
message = client.messages.create(
model="claude-sonnet-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
message = client.messages.create(
model="claude-sonnet-5",
max_tokens=1024,
tools=[{
"name": "get_weather",
"description": "Get the weather for a location",
"input_schema": {
"type": "object",
"properties": {
"location": {"type": "string"}
},
"required": ["location"]
}
}],
messages=[{"role": "user", "content": "What's the weather in Tokyo?"}]
)
for block in message.content:
if block.type == "tool_use":
print(block.name)
print(block.input)延伸思考
message = client.messages.create(
model="claude-opus-5",
max_tokens=16000,
thinking={
"type": "enabled",
"budget_tokens": 10000
},
messages=[{"role": "user", "content": "Solve this complex problem step by step."}]
)
for block in message.content:
if block.type == "thinking":
print(block.thinking)
elif block.type == "text":
print(block.text)建議使用的 Claude 模型
| 模型 | 最適合用於 |
|---|---|
claude-opus-4-6 | 深度推理、長篇分析 |
claude-sonnet-4-6 | 程式撰寫、一般助理任務 |
claude-haiku-4-5 | 快速、輕量的回應 |