adw.adw_435

Active

Tool of AlpineDataWorks Intelligence Server

declared in 0.3.0

Returns a 0-100 AI inference cost-efficiency score for text-output models (blended USD per million tokens from the OpenRouter catalog, 90-day window z-scored against baseline) with recent median and p10-floor prices, baseline median, and z_median/z_p10_floor/z_composite. Call when the user asks about LLM pricing trends, cost per token, or whether inference is getting cheaper, or when timing model-routing changes, committed-spend negotiations, or AI COGS forecasts. Updates: daily.

Parameters schema

{
  "type": "object",
  "required": [],
  "properties": {
    "days": {
      "type": "integer",
      "maximum": 1825,
      "minimum": 1,
      "description": "Optional: return a daily HISTORY series of the last N days (up to 5 years of real archived data) instead of the current snapshot. History requires Gold tier; without it, the current snapshot is returned."
    }
  }
}

What this tool wraps· 1 endpoint

min confidence0.70 0.50

Data resourceOpenRouter API
OpenRouter · ai
name mention0.70

Parent server

AlpineDataWorks Intelligence Server

1/7 registries

View full server →