TrustLayer AI- Control Plane for Safe LLMs & Agents
TrustLayer is an API-first security control plane for LLM apps and AI agents. It blocks prompt injection attacks, detects agent drift, and gives you a kill switch for production incidents. Why TrustLayer: - Prompt injection + jailbreak detection - Contract testing (multi-check safety scans) - Drift detection for agents over time - Incident lockdown (kill switch) - Policy-as-code for security…
TrustLayer AI- Control Plane for Safe LLMs & Agents endpoints
| Method | Endpoint | Description |
|---|---|---|
| health | ||
| GET |
healthCheck /health |
|
| v2 | ||
| POST |
incidentUnlock /v2/incident/unlock |
|
| POST |
checkDrift /v2/drift/check |
|
| POST |
setDriftBaseline /v2/drift/baseline |
|
| POST |
runContracts /v2/contracts |
|
| GET |
exportAudit /v2/audit/export.csv |
|
| POST |
uploadPolicy /v2/policy/upload |
|
| GET |
incidentStatus /v2/incident/status |
|
| GET |
getPolicy /v2/policy |
|
| GET |
getDriftEvents /v2/drift/events |
|
| POST |
incidentLockdown /v2/incident/lockdown |
|
| POST |
scanPrompt /v2/scan |
|
TrustLayer AI- Control Plane for Safe LLMs & Agents pricing
| Plan | Price | Rate limit | Quotas |
|---|---|---|---|
| BASIC | Free | — |
|
| PRO Recommended | $49 / month | 5 / second |
|
| ULTRA | $199 / month | 20 / second |
|
| MEGA | $499 / month | 50 / second |
|