langfuse-cost-tuning
Monitor and optimize LLM costs using Langfuse analytics and dashboards. Use when tracking LLM spending, identifying cost anomalies, or implementing cost controls for AI applications. Trigger with phrases like "langfuse costs", "LLM spending", "track AI costs", "langfuse token usage", "optimize LLM budget".
- License 许可
- MIT
- 最近更新
- 2026-05-26
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- langfuse-cost-tuning
- author
- Jeremy Longshore <jeremy@intentsolutions.io>
- license
- MIT
- version
- 1.0.0
- description
- Monitor and optimize LLM costs using Langfuse analytics and dashboards. Use when tracking LLM spending, identifying cost anomalies, or implementing cost controls for AI applications. Trigger with phrases like "langfuse costs", "LLM spending", "track AI costs", "langfuse token usage", "optimize LLM budget".
- allowed-tools
- Read, Write, Edit
- compatible-with
- claude-code, codex, openclaw
02 资源文件 1
- 参考文档references/implementation.md6.9 KB
03 SKILL.md 正文
Langfuse Cost Tuning
Contents
Overview
Track, analyze, and optimize LLM costs using Langfuse observability data with token tracking, cost alerts, model selection optimization, and automated reporting.
Prerequisites
- Langfuse tracing with token usage
- Understanding of LLM pricing models
- Access to Langfuse analytics dashboard
Instructions
Step 1: Track Token Usage in Generations
Record prompt and completion tokens on each generation.end() call. Calculate cost using per-model pricing tables and store as metadata.
Step 2: Create Cost Dashboard Queries
Fetch generations from Langfuse and aggregate costs by model, by day, and by token type. Calculate total cost and generation count.
Step 3: Implement Cost Alerts
Build a CostMonitor that tracks hourly and daily spend. Define thresholds (e.g., $100/day warn, $500/day notify, $1/request warn). Send Slack/PagerDuty notifications on breaches.
Step 4: Optimize Model Selection
Route simple tasks (summarize, classify, extract) and short inputs to cheaper models (GPT-4o-mini). Reserve expensive models for complex tasks (analyze, reason, code).
Step 5: Add Caching and Prompt Optimization
Cache LLM responses with TTL. Strip redundant whitespace and filler words from prompts to reduce token count.
See detailed implementation for advanced patterns.
Output
- Token usage tracking per generation
- Cost analytics aggregation
- Real-time cost alerts
- Smart model selection
- Response caching and prompt optimization
Error Handling
| Issue | Cause | Solution |
|---|---|---|
| Missing usage data | SDK not capturing | Verify generation.end() includes usage |
| Inaccurate costs | Wrong pricing | Update MODEL_PRICING regularly |
| Budget exceeded | No alerts | Implement cost alerts |
| Report failures | API limits | Add pagination to fetchGenerations |
Examples
LLM Cost Reference
| Model | Input (per 1M) | Output (per 1M) |
|---|---|---|
| GPT-4 Turbo | $10.00 | $30.00 |
| GPT-4o | $5.00 | $15.00 |
| GPT-4o-mini | $0.15 | $0.60 |
| Claude 3 Opus | $15.00 | $75.00 |
| Claude 3 Sonnet | $3.00 | $15.00 |
| Claude 3 Haiku | $0.25 | $1.25 |
Cost Optimization Strategies
| Strategy | Potential Savings | Effort |
|---|---|---|
| Model downgrade | 50-90% | Low |
| Prompt optimization | 10-30% | Low |
| Response caching | 20-60% | Medium |
| Batch processing | 10-20% | Medium |
Resources
04 同仓库更多 Skills
zustand-store-ts
Create Zustand stores with TypeScript, subscribeWithSelector middleware, and proper state/action separation. Use when building React state management, creating global stores, or implementing reactive state patterns with Zustand.
zustand-store-creator
Zustand Store Creator - Auto-activating skill for Frontend Development. Triggers on: zustand store creator, zustand store creator Part of the Frontend Development skill category.
zero-trust-config-helper
Zero Trust Config Helper - Auto-activating skill for Security Advanced. Triggers on: zero trust config helper, zero trust config helper Part of the Security Advanced skill category.
zapier-integration-helper
Zapier Integration Helper - Auto-activating skill for Business Automation. Triggers on: zapier integration helper, zapier integration helper Part of the Business Automation skill category.
zai-cli
Execute z.AI CLI providing vision, search, reader, and GitHub exploration via CLI and MCP. Use when user needs image/video analysis, OCR, UI-to-code conversion, error diagnosis, real-time web search, web page to markdown extraction, or GitHub code exploration. Trigger with phrases like "analyze this image", "search the web for", "read this page", "explore this repo", or "use zai". Requires Z_AI_API_KEY.
yt-research
Research competitor YouTube channels, niches, and trending topics for your content strategy. Use this skill whenever the user says "research channels", "analyze competitors", "find trending topics", "niche analysis", "competitive research", "what are other creators doing", "scrape YouTube channels", or wants to understand the competitive landscape for a specific tool or topic area. Use when working with yt research. Trigger with 'yt', 'research'.