DeepSeek API：Pro、Flash 区别与 SDK 接入

curl --fail-with-body --max-time 120 https://api.apizt.com/v1/chat/completions \
  -H "Authorization: Bearer $tokenba_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4-pro","max_tokens":4096,"messages":[{"role":"user","content":"Find the bug and propose tests for Python code: def average(xs): return sum(xs)/len(xs). Cover empty input, one number and negative numbers. Do not execute code."}]}'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["tokenba_API_KEY"],
    base_url="https://api.apizt.com/v1",
    timeout=120.0,
)
result = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Given these requirements: an invoice cannot have a negative total; zero totals are allowed; totals use decimal arithmetic. Produce a short review checklist and three boundary tests."}],
    max_tokens=4096,
)
choice = result.choices[0]
print(choice.message.content)
print("finish_reason:", choice.finish_reason)
print("usage:", result.usage)
if not choice.message.content or choice.finish_reason == "length":
    raise RuntimeError("Check the output budget and channel settings before retrying")