See the cost, latency, and quality of every LLM call. Catch bad output before your users do.
| Tailor made for
“Caught a 10× cost regression 3 days after shipping. Foglamp paid for itself in week one.”
Instrument once. Get cost, traces, evals, alerts, and per-agent spend on every call.
Two lines instruments every generateText / streamText call.
import { foglamp } from "foglamp"const fog = foglamp()
Per-agent spans, latency, and spend - with the full call flow.
Score production traffic with code checks and LLM judges.
Waterfall every run, with the exact prompt and response per span.
Threshold rules on cost, latency, and error rate.
Know exactly what every call costs — by model, agent, customer.
Claude Opus 4.8$323.12
Gemini 3.5 Pro$43.06
Total$1,248.50$1,248.50
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。