Observability
Full trace visibility across every LLM call
Every token, latency, and dollar attributed to the exact agent node that spent it. Unlimited traces on every plan — retention is the only paid axis.
Fluiq/ traces247 rpm · live
All modelsAny statusAny security247 traces
| FUNCTION | MODEL | LATENCY | COST | SOURCE |
|---|---|---|---|---|
| answer_question | gpt-4o | 1,243ms | $0.012 | LangChain |
| search_docs | claude-3.5-s | ⚡ cached | $0.000 | Cached |
| generate_report | gpt-4o | 2,108ms | $0.041 | OpenAI |
| classify_intent | gemini-1.5 | 890ms | $0.005 | |
| answer_question | gpt-4o | 1,540ms | $0.019 | LangChain |
What you get
Attribution
Per-node token and cost
Token counts and USD cost at live provider rates, attributed down to the span that spent them.
Latency
p50 / p95 / p99
Latency histograms per agent and per model, so you watch the tail, not just the average.
Multi-agent
Real DAGs, not flat lists
Fan-outs, joins, and loop-backs across LangGraph, CrewAI, and Google ADK render as the graph your agents actually executed.
Live
Real-time streaming
Traces land on the dashboard as calls complete. Watch a run unfold instead of refreshing.
One decorator turns any call into a span.
- Patches OpenAI, Anthropic, Gemini, LangChain, and vector stores automatically
- Nested calls build a full span tree with parent and child timing
- Cost is computed at live provider rates, per model
app.py
import fluiq
fluiq.instrument(api_key="fl_...")
@fluiq.trace
def answer(question: str) -> str:
docs = store.search(question, k=5)
return llm.invoke(prompt(question, docs))
# Traced with cost, latency, and a full span treePart of the Fluiq platform
Compare plansSecurityBlock attacks, redact PII and secrets.ExploreOptimizationCache repeated prompts automatically.ExploreEvaluationScore responses and whole agent runs.ExploreDatasetsGolden sets that capture whole agent runs.ExplorePrompt ManagementVersion and deploy prompt templates.ExploreAlertsPush eval and security events to Slack.Explore
Unlimited traces, always free.
Start on the free tier and turn on each pillar as your pipeline grows. No code changes required.