SDKs nativos
SDK da Anthropic
Use o TokenLab com o SDK da Anthropic para compatibilidade nativa com a Messages API do Claude
Visão geral
O TokenLab oferece suporte ao caminho nativo da Messages API da Anthropic, para que você possa usar diretamente o SDK oficial da Anthropic com modelos Claude.
Para o SDK da Anthropic, use https://api.tokenlab.sh como base URL, sem adicionar /v1 manualmente.
Entre as rotas de SDK documentadas, este é um dos caminhos do TokenLab com melhor suporte para recursos nativos do Claude.
Instalação
pip install anthropicConfigurar o Client
from anthropic import Anthropic
client = Anthropic(
api_key="sk-your-tokenlab-key",
base_url="https://api.tokenlab.sh",
)Uso básico
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)Visão
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
}
}
]
}]
)Uso de ferramentas
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)Thinking estendido
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)Modelos Claude recomendados
| Modelo | Melhor para |
|---|---|
claude-opus-4-6 | Raciocínio profundo, análise longa |
claude-sonnet-4-6 | Programação, tarefas gerais de assistente |
claude-haiku-4-5 | Respostas rápidas e leves |