Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.medera.info/llms.txt

Use this file to discover all available pages before exploring further.

The Medera API is split across two services:
ServicePortPurpose
Backend3001Tenant + PHI persistence, workflow + deployment lifecycle, EHR + billing integration, Socket.IO
AI Services8000Multimodal engines, RDoC, Care Orchestrator, Vapi orchestration, clinical NLP
In production the public host is api.medera.ai and routes to both services through the API gateway.

​
Base URLs

EnvironmentBackend hostAI Services host
Productionhttps://api.medera.aihttps://api.medera.ai (proxied)
Staginghttps://staging.api.medera.aihttps://staging.api.medera.ai
Sandboxhttps://sandbox.api.medera.aihttps://sandbox.api.medera.ai
Internally:
  • Backend: http://localhost:3001 (dev) / http://backend:3001 (Docker)
  • AI Services: http://localhost:8000 (dev) / http://ai-services:8000 (Docker)

​
Authentication

SurfaceCredentialHeader
End-user requestsClerk JWTAuthorization: Bearer <jwt>
Server-to-serverDeveloper API KeyX-API-Key: <key>
Service-to-serviceInternal service keyX-Service-Key: <key> (internal only)
See Authentication Overview.

​
Content type

Request and response bodies are JSON. File uploads use multipart/form-data. Recordings, audio, and video uploads use multer (Backend) or UploadFile (AI Services) — max 150 MB per file.

​
Rate limits

See Rate Limits.

​
Error format

{
  "error": {
    "code": "rls_denied",
    "message": "Access to resource is denied by tenant policy.",
    "request_id": "req_abc123"
  }
}
See Errors.