Anthropic Claude Monitoring & Tracing
Auto-instrument every Claude API call (Messages, streaming, and the Beta client) with zero code changes. See prompt cache hits, token costs at Anthropic's rates, and security events on every request.
Free tier · No credit card · 2-minute setup
What you get with Fluiq for Anthropic
Prompt cache visibility
See exactly how many tokens were served from Anthropic's prompt cache (cache_read vs cache_creation) on every request, and what you saved on each call.
Cost at Claude rates
Input, output, and cache token costs calculated at Anthropic's published per-token rates for each Claude model, attributed per trace and aggregated by day.
Security scanning
Prompt injection, jailbreak scoring, and PII detection run server-side on every Claude request, in warn mode to flag, or block mode to intercept before the API call.
Add Fluiq to your Anthropic app in 2 lines
import fluiq
fluiq.instrument(api_key="fl_...") # patches anthropic automatically
import anthropic
client = anthropic.Anthropic()
# Messages API, fully traced with cache visibility:
message = client.messages.create(
model="claude-opus-4-8",
max_tokens=1024,
messages=[{"role": "user", "content": "Summarise this document"}],
)
# Streaming is also traced:
with client.messages.stream(model="claude-opus-4-8", max_tokens=256,
messages=[{"role": "user", "content": "Hello"}]) as stream:
for text in stream.text_stream:
print(text, end="", flush=True)What Fluiq instruments in Anthropic
Every call to these methods is automatically traced, no decorators, no wrappers, no manual spans.
anthropic.messages.create()anthropic.messages.stream()anthropic.messages.acreate()anthropic.beta.messages.create()anthropic.beta.messages.stream()anthropic.messages.batches.create()Start tracing Anthropic in 2 minutes
Free tier. No credit card. Full traces, security scanning, and evals on your first Anthropic call.
Unlimited free traces · 1,000 evals / month · 14-day retention