token-optimizer

Reduce LLM API costs via semantic caching, prompt compression, model routing and context pruning. Zero code changes required.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://token-optimizer--prompt_thin.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "token-optimizer": {
      "url": "https://token-optimizer--prompt_thin.run.tools"
    }
  }
}

能力清单

工具	说明
proxy_chat	Send a chat completion request through PromptThin's cost-saving proxy. Five optimization routes are applied automatically: (A) semantic cache, (B) prompt compression via LLMLingua 2, (C) model routing to cheaper models, (D) context pruning at 8K tokens, (E) thinking budget caps on reasoning models based on task complexity. Use this instead of calling OpenAI, Anthropic, Gemini, or Groq directly. Returns the LLM response with a cost summary.
proxy_predict	Estimate cost savings BEFORE making a real LLM call — completely free, no tokens consumed. Returns original token count, estimated tokens after savings, cost comparison, saving percentage, applicable methods, and a recommendation.
billing_start_trial	Start a 7-day free Pro trial. Returns a Stripe checkout URL. No charge for 7 days. Pro plan: $4.99 first month, then $11.99/month. 10,000 requests/month. Cancel anytime.
usage_summary	Retrieve complete usage summary: total requests, cache hit rate, total tokens saved, estimated cost saved in USD, and requests routed to cheaper models.
billing_status	Retrieve current plan, monthly request limit, requests used this month, remaining requests, and usage percentage. Warns when usage exceeds 80%.
cache_flush	Mark all cached responses as stale, forcing fresh LLM calls. Use after updating a knowledge base or changing system prompts.
usage_recent	Retrieve recent proxied API requests with timestamp, provider, model, token counts, cache hit status, routing info, and tokens saved.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。