在 Python 中限制 LLM 批处理的成本：账本与硬预算

import json
import os
from pathlib import Path

from openai import OpenAI

client = OpenAI(
    base_url='https://api.cheaptokens.dev/v1',
    api_key=os.environ['CHEAPTOKENS_API_KEY'],
)
MODEL = 'deepseek-ai/DeepSeek-V4-Flash-0731'
PRICE_IN, PRICE_OUT = 1.00, 2.00  # USD per 1M tokens: example, substitute current ones


class BudgetExceeded(Exception):
    pass


class Ledger:
    def __init__(self, path, budget_usd):
        self.path = Path(path)
        self.budget = budget_usd
        self.rows = []
        if self.path.exists():
            with self.path.open() as f:
                self.rows = [json.loads(line) for line in f if line.strip()]

    @property
    def spent(self):
        return sum(r['cost_usd'] for r in self.rows)

    def done(self):
        return {r['unit'] for r in self.rows}

    def check(self, unit):
        if self.spent >= self.budget:
            raise BudgetExceeded(
                f'stopped before {unit}: spent {self.spent:.4f} of {self.budget} USD'
            )

    def add(self, unit, usage, finish_reason):
        cost = (usage.prompt_tokens * PRICE_IN
                + usage.completion_tokens * PRICE_OUT) / 1_000_000
        row = {
            'unit': unit,
            'model': MODEL,
            'prompt_tokens': usage.prompt_tokens,
            'completion_tokens': usage.completion_tokens,
            'finish_reason': finish_reason,
            'cost_usd': round(cost, 6),
        }
        self.rows.append(row)
        with self.path.open('a') as f:
            f.write(json.dumps(row) + '\n')


def ask(ledger, unit, prompt, max_tokens=400):
    ledger.check(unit)
    resp = client.chat.completions.create(
        model=MODEL,
        messages=[{'role': 'user', 'content': prompt}],
        max_tokens=max_tokens,
    )
    ledger.add(unit, resp.usage, resp.choices[0].finish_reason)
    return resp.choices[0].message.content

prompts = {
    'doc-001': 'Summarize this ticket in one sentence: ...',
    'doc-002': 'Summarize this ticket in one sentence: ...',
    # ... your 200 prompts
}

ledger = Ledger('ledger.jsonl', budget_usd=0.50)
already = ledger.done()

for unit, prompt in prompts.items():
    if unit in already:
        continue
    try:
        answer = ask(ledger, unit, prompt)
    except BudgetExceeded as e:
        print(e)
        break
    Path(f'out-{unit}.txt').write_text(answer)

rows = [json.loads(line) for line in open('ledger.jsonl')]
for r in sorted(rows, key=lambda r: r['cost_usd'], reverse=True)[:5]:
    print(r['unit'], r['prompt_tokens'], r['completion_tokens'], r['finish_reason'])