DeepSeek V4.1 Flash 经济版上线：同一份权重，全时段 8 折

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["APIYI_API_KEY"],
    base_url="https://api.apiyi.com/v1",
)

resp = client.chat.completions.create(
    model="deepseek-v4-1-flash-economy-261017",
    messages=[
        {"role": "system", "content": "你是数据清洗助手，只输出 JSON。"},
        {"role": "user", "content": "把下面这段客服记录提取成 {问题, 结论, 情绪} 三个字段：……"},
    ],
    reasoning_effort="none",   # 关闭思考，批量任务省下大量 output token
    max_tokens=1024,
)
print(resp.choices[0].message.content)

resp = client.chat.completions.create(
    model="deepseek-v4-1-flash-economy-261017",
    messages=[{"role": "user", "content": "分析这份财报的三个主要风险点：……"}],
    reasoning_effort="high",
    max_tokens=8192,
)

from concurrent.futures import ThreadPoolExecutor

def run_one(text: str) -> str:
    r = client.chat.completions.create(
        model="deepseek-v4-1-flash-economy-261017",
        messages=[{"role": "user", "content": text}],
        reasoning_effort="none",
        max_tokens=512,
    )
    return r.choices[0].message.content

with ThreadPoolExecutor(max_workers=16) as pool:
    results = list(pool.map(run_one, batch_texts))