備援額度

client = Anthropic()

request = {
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello, Claude"}],
}


def send(model, body):
    return client.beta.messages.create(
        model=model, betas=["fallback-credit-2026-06-01"], **body
    )


response = send("claude-fable-5", request)

if (
    response.stop_reason == "refusal"
    and (details := response.stop_details)
    and (token := details.fallback_credit_token)
):
    exact_body = request | {"fallback_credit_token": token}
    # 除非該宣告為 False，否則優先採用延續形式
    if details.fallback_has_prefill_claim is not False:
        # 回傳拒絕內容，並去除最後一個文字區塊的尾端空白
        # （預填驗證器會拒絕它；伺服器端的比對則容許此修改）。
        # 使用工具的請求也會省略未配對的 tool_use 區塊，
        # 並在省略後再次去除空白。
        echoed = [block.model_dump() for block in response.content]
        match echoed:
            case [*_, {"type": "text"} as final_block]:
                final_block["text"] = final_block["text"].rstrip()
        attempt = exact_body | {
            "messages": [
                *request["messages"],
                {"role": "assistant", "content": echoed},
            ]
        }
    else:
        attempt = exact_body

    try:
        response = send("claude-opus-4-8", attempt)
    except BadRequestError as error:
        if "redemption temporarily unavailable" in str(error):
            raise  # Transient: retry with the token within its five-minute window
        try:
            # 退回至未變更的主體，仍保留該 token
            response = send("claude-opus-4-8", exact_body)
        except BadRequestError as error:
            if "redemption temporarily unavailable" in str(error):
                raise  # Transient: retry with the token within its five-minute window
            # 該 token 本身遭拒：捨棄它並在不含它的情況下重試。
            response = send("claude-opus-4-8", request)

print(json.dumps({"stop_reason": response.stop_reason, "model": response.model}))