LLM Cost Tracker — LLM Cost 追踪er

API Cost 追踪er

监控 and 优化 your LLM API spending directly from your 代理.

Quick 启动

运行 cost analysis:

python3 scripts/cost_追踪er.py --summary

Commands 检查 Current Spend python3 scripts/cost_追踪er.py --提供者 openAI --period today python3 scripts/cost_追踪er.py --提供者 anthropic --period week python3 scripts/cost_追踪er.py --all --period month

设置 Bud获取 Alert python3 scripts/cost_追踪er.py --设置-bud获取 100 --period month --alert telegram

Cost Breakdown by 模型 python3 scripts/cost_追踪er.py --breakdown 模型 --period week

Optimization Recommendations python3 scripts/cost_追踪er.py --优化

This analyzes usage patterns and recommends:

模型 降级s for simple tasks (e.g., use HAIku instead of Opus for classification) Caching opportunities (repeated similar prompts) Batch processing windows (off-peak pricing where avAIlable) 上下文 window optimization (trim unnecessary 上下文) Supported 提供者s 提供者 Method 设置up OpenAI Usage API OPENAI_API_KEY env var Anthropic Usage API ANTHROPIC_API_KEY env var Google AI Billing API GOOGLE_API_KEY env var DeepSeek Usage API DEEPSEEK_API_KEY env var Bud获取 Alerts

配置 in ~/.OpenClaw/cost-追踪er.json:

{ "bud获取s": { "dAIly": 10, "weekly": 50, "monthly": 200 }, "alertChannels": ["telegram", "discord"], "alertThresholds": [50, 75, 90, 100] }

Alerts fire at each threshold percentage. At 100%, optionally 暂停 non-critical 代理 tasks.

输出 格式化

报告s 生成 as markdown tables suitable for any messaging surface:

提供者 | 模型 | 令牌s | Cost ------------|--------------------|-----------|--------- Anthropic | claude-opus-4-6 | 2.1M | $63.00 Anthropic | claude-sonnet-4-6 | 5.4M | $16.20 OpenAI | gpt-4o | 1.8M | $9.00 | TOTAL | | $88.20

Advanced: Cost Optimization Patterns

See references/optimization-图形界面de.md for detAIled strategies on reducing API spend by 30-60% without sacrificing 质量.