Retell AI home page
Search...
Ctrl K
Ask AI
Homepage
Support
Compliance
Dashboard
Dashboard
Search...
Navigation
Latency
Check actual latency
Documentation
API Reference
Video Tutorials
Deprecation Notice
Community
Changelog
Status
Pricing
Enterprise Plan
Introduction
Get Started
Build your first phone agent in 5 minutes
SDKs
Build
Setup conversation flow agent
Setup single / multi prompt agent
Create chat agent
Set language for your agent
Understand user speech better
Generate better responses from LLM
Customize the synthesized speech
Integrate telephony features
Provide context to the agent
Test
Testing Overview
LLM Playground
LLM Simulation Testing
Audio Testing
Deploy
Purchase phone number
Connect to custom telephony providers via SIP
Make & receive phone calls
Create Chat Completion
Retell Chat Widget
Enable SMS capabilities
Setup versioning for agents
Batch Calls
Increase call pickup rate
Connect to web call
Understand concurrency & limits
Monitor
Monitor sessions via dashboard
Get analytics insight
Register & handle webhooks
Post Call Analysis
Reliability & Debugging
Reliability Overview
Latency
Check estimated latency
Check actual latency
Troubleshoot high latency
Fix agent behaviors
Debug phone call issues
Accounts and Workspace
Workspace
Account
Billing
Keys
Privacy
Advanced Topics
Custom LLM
Audio Basics
Network Ecosystem
Partner Program
Affiliate Program
On this page
Understanding Latency Metrics
Key Metrics Explained
Latency
Check actual latency
You can monitor the latency of individual calls in the “Call History” section.
Call History
Understanding Latency Metrics
End-to-end latency measures the total time from when the user stops speaking until the AI agent begins responding. This includes processing time, network delays, and model inference time.
Key Metrics Explained
P90 (90th Percentile)
: 90% of calls have latency below this value.
Median (50th Percentile)
: Half of the calls have latency less than this value
Min
: The fastest response time achieved in any call.
Was this page helpful?
Yes
No
Check estimated latency
Troubleshoot high latency
Assistant
Responses are generated using AI and may contain mistakes.