Model Output Tokens to Generate Time-to-First-Token (ms) Per-Token Latency (ms) Concurrent Requests

TTFT

0ms

Total Time

0ms

Throughput

0 t/s

Tokens/Sec

⚡ Latency Breakdown

Time to First Token (TTFT)

0ms

User perceives response start after this delay. Lower is better for UX.

Token Generation Time

0ms

Time to generate remaining tokens after first token.

Total Response Time

0ms

Complete time from request to final token streamed to user.

🚀 Throughput Analysis

Tokens/Second

0 t/s

Requests/Hour

With Concurrency

0 req/hr

⏱️ Response Timeline

0ms

Request arrives at model

80ms

First token generated and streamed to client

10,000ms

Final token streamed, request complete

📊 Performance Summary

💡 Optimization Tips