# Do I need my own LLM provider key for Tessary to grade traces?

On a self-hosted install, yes. Your org adds at least one model provider's own key, and that's what funds the judgment step.

The five classifiers on by default don't call a model, so your provider choice doesn't affect them. Two you switch on yourself work differently. [Frustration](/answers/tessary-frustration/what-is-tessarys-frustration-classifier) runs on an OpenRouter or TypeSafe key: every message it scores is a call on that key, and if the key is refused or removed it pauses and says so until one works. [Groundedness](/answers/tessary-groundedness/what-is-tessarys-groundedness-classifier) needs no provider key. It scores answers with a public model you run on a Mac with Apple silicon or a GPU instance on AWS, and while that model is down it pauses, then scores what it missed once the model answers again.

[Your model-provider spend is the real cost line here](/answers/tessary-classifiers/how-much-does-it-cost-to-run-a-classifier-on-every-trace). The LLM judgment that reads what the classifiers flag resolves to whichever provider your org holds a credential for, in a fixed priority order, and on a self-hosted install with none configured that step fails closed.

---

Source: https://tessary.ai/answers/tessary-classifiers/do-i-need-my-own-llm-provider-key-for-tessary-to-grade-traces
More on Tessary classifiers: https://tessary.ai/answers/tessary-classifiers
From Tessary, agent reliability for AI agents in production: https://tessary.ai