{"name":"AI Prompt Optimizer API","version":"2.0.0","description":"Deterministic prompt analysis: token estimation, filler detection, clarity scoring, and rewriting. No LLM calls — runs on edge, sub-10ms.","endpoints":{"optimize":"POST /optimize — rewrite prompt, return token savings","analyze":"POST /analyze — issues, clarity score, suggestions","estimate_tokens":"POST /estimate-tokens — single or batch (max 50)","compare":"POST /compare — compare two prompts, return winner","mcp":"POST /mcp — JSON-RPC 2.0 MCP server","openapi":"GET /openapi.json"},"note":"All endpoints also accept GET with ?prompt= for quick testing."}