Trace p50
3.43s
typical trace
Trace p95
6.19s
tail latency
Trace p99
7.35s
worst 1%
Slowest model
claude-opus-4-7
p95 2.38s
Time budget · LLM vs tool
Anything outside these bars is your own code.
LLM time86%
Tool time14%
Diagnostic
LLM calls are 86% of in-trace time. Model choice or prompt length is the right place to optimize.
Latency by model
| Model | Calls | Mean | p50 | p95 | p99 |
|---|---|---|---|---|---|
| claude-opus-4-7 | 265 | 1.49s | 1.51s | 2.38s | 2.48s |
| gpt-4o | 135 | 1.30s | 1.17s | 2.36s | 2.42s |
| claude-sonnet-4-6 | 71 | 1.46s | 1.50s | 2.36s | 2.39s |
| gpt-4-mini | 60 | 1.39s | 1.44s | 2.35s | 2.49s |
Slowest traces · last 24h