Architecture deep dive

How ModelRiver works

Choose the request pattern that fits your architecture. See exactly how data flows from your frontend to AI and back.

1
Recommended

Event-driven async

Real-time updates via WebSocket. Backend callbacks for processing. Best for interactive apps.

Learn more
2

Async (Dual-Delivery)

Fire and forget. Results delivered simultaneously to your webhook and browser. Best for reliable background ops.

Learn more
3

Sync

Simple request/response. Blocks until complete. Best for quick operations.

Learn more

Event-driven async flow

Step-by-step interactive data flow visualization

1
User prompt
Frontend interaction
2
Your backend
API call to MR
3
ModelRiver
Orchestration
4
AI providers
Auto-failover flow
Async workflow triggered
6
Webhook delivery
Callback to your server
5
ModelRiver
Message orchestration
7
User's browser
Real-time WS update
Your code
ModelRiver
AI providers
Async / WebSocket

Why event-driven async?

Fast Acknowledgment

Immediate response with channel ID. No waiting for AI completion.

Background Execution

AI runs in background. Your server stays responsive.

Automatic Fallback

Automatic retries with fallback providers. Built-in reliability.

Real-time

WebSocket delivery to frontend. Users see results instantly.

Ready to get started?

Start free Read docs