快速模式（研究预览版）

client = anthropic.Anthropic()

response = client.beta.messages.create(
    model="claude-opus-5",
    max_tokens=4096,
    speed="fast",
    betas=["fast-mode-2026-02-01"],
    messages=[
        {"role": "user", "content": "Refactor this module to use dependency injection"}
    ],
)

for block in response.content:
    if block.type == "text":
        print(block.text)

client = anthropic.Anthropic()

response = client.beta.messages.create(
    model="claude-opus-5",
    max_tokens=1024,
    speed="fast",
    betas=["fast-mode-2026-02-01"],
    messages=[{"role": "user", "content": "Hello"}],
)

print(response.usage.speed)  # "fast" or "standard"

client = anthropic.Anthropic()


def create_message_with_fast_fallback(max_retries=0, max_attempts=3, **params):
    try:
        return client.with_options(max_retries=max_retries).beta.messages.create(
            **params
        )
    except anthropic.RateLimitError:
        if params.get("speed") == "fast":
            del params["speed"]
            return create_message_with_fast_fallback(max_retries=max_retries, **params)
        raise
    except (
        anthropic.APIStatusError,
        anthropic.APIConnectionError,
    ) as error:
        if isinstance(error, anthropic.APIStatusError) and error.status_code < 500:
            raise
        if max_attempts > 1:
            return create_message_with_fast_fallback(
                max_retries=max_retries, max_attempts=max_attempts - 1, **params
            )
        raise


message = create_message_with_fast_fallback(
    model="claude-opus-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
    betas=["fast-mode-2026-02-01"],
    speed="fast",
    max_retries=0,
)