Fast Acknowledgment
Return a response immediately while AI continues working in the background. Your users don't have to wait for long-running AI tasks to finish.
Async webhooks
Async Webhooks Pattern
Send one AI request, then let ModelRiver deliver the final result to both your backend and connected users automatically. Ideal for reliable background processing.
1
Recommended
Backend pipeline
Live progress updates, background AI workflows, and backend processing. Best for interactive AI applications.
Learn more2
Async (Dual-Delivery)
Submit once, then automatically deliver results to both your backend and your users. Best for reliable asynchronous processing.
Learn more3
Sync
Wait for AI to finish before returning the result. Best for quick AI requests and straightforward integrations.
Learn moreAsync dual-delivery flow
Send the final result to your backend and your users at the same time.
AI finishes once and updates both your backend and connected users immediately.
1
Your backend
Sends AI request
2
ModelRiver
Coordinates AI requests
3
AI providers
AI generates a response
4
Your webhook
Your backend gets the result
5
User's browser
User sees the update instantly
Architecture
Why dual-delivery async?
AI finishes once, then ModelRiver delivers the result to both your backend and your users. Your application stays responsive while everyone receives updates automatically.
Background Execution
Run large AI tasks in the background instead of slowing down your backend. Your application stays responsive while ModelRiver manages the heavy AI work.
Automatic Fallback
If one AI provider becomes slow or unavailable, ModelRiver automatically switches to another so your workflows continue without interruption.
Live progress updates
Show progress and final results as soon as they're available. Users see updates instantly without refreshing the page.