SDK native

Anthropic SDK

Gunakan Claude Messages melalui TokenLab dengan Anthropic SDK

Gambaran Umum

Anthropic SDK dapat memanggil model Claude melalui Messages API milik TokenLab. Cukup ubah API key dan base URL; metode SDK tetap sama.

Untuk Anthropic SDK, gunakan https://api.tokenlab.sh sebagai base URL, tanpa menambahkan /v1 secara manual.

Instalasi

pip install anthropic

Konfigurasi Client

from anthropic import Anthropic

client = Anthropic(
    api_key="sk-your-tokenlab-key",
    base_url="https://api.tokenlab.sh",
)

Penggunaan Dasar

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)

Streaming

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)

Vision

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
                }
            }
        ]
    }]
)

Penggunaan Tool

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)

Pemikiran Diperluas

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)

Memilih Model

Salin ID model Claude saat ini dari halaman Model. Bandingkan model dengan prompt Anda sendiri sebelum menetapkan default.

Pemecahan Masalah

Di halaman ini