Show HN: Tracking GenAI cost and endpoint fragility so app teams don't have to

Category: observability

Tags: llm-observability, cost-tracking, genai, telemetry, dashboard

Score: 4.7/10 (Innovation: 4, Technical: 5, Documentation: 2, Utility: 5)

LLMIntel is a cost and lifecycle observability dashboard for GenAI API usage, tracking spend across providers, models, and custom tags while flagging models nearing retirement. It targets application teams that need visibility into LLM spend allocation and deprecation risk, though the public artifact is a demo without open-source code.

Target audience: backend devs, platform engineers, devops, engineering managers

Repository: https://llmintel.ai/demo

View on Hacker News