pdxlab/TrustModel AI Eval

Evaluate your AI model for trust, safety, and bias. 10 dimensions. First scan free. Gate your pipeline on trust scores.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
api-keyTrustModel API key (get one at trustmodel.ai/developer)yes
model-nameName of the AI model to evaluateyes
model-typeType of model: chat, completion, embedding, classification, agentnochat
dimensionsComma-separated dimensions to evaluate (default: all 10). Options: safety, fairness, accuracy, privacy, transparency, robustness, accountability, explainability, compliance, reliabilitynoall
min-scoreMinimum trust score to pass (0.0 - 1.0). Action fails if score is below this threshold.no0.0
endpoint-urlModel API endpoint URL (for custom model evaluation)no""
free-scanUse FreeScan (first eval free per model, no credits needed)notrue
fail-on-errorFail the action if the API call errors (vs just warning)nofalse
namedescription
trust-scoreOverall trust score (0.0 - 1.0)
passedWhether the model passed the minimum score threshold (true/false)
dimensions-jsonJSON object with per-dimension scores
report-urlURL to the full evaluation report on TrustModel console
summaryHuman-readable summary of the evaluation