0% platform fee — first 1,000,000 customersClaim 0% fee
Observability

Every request, fully visible.

Logs, alerts, and callbacks for every LLM call. See what happened, get notified when things break, pipe data to your existing tools. Cost is the provider’s number — never ours, never reconstructed.

request_log · 12:04:31

Latest request

request_idreq_a1b2c3d4
modelgemini-2.5-flash
status200
latency (total)0.6 s
TTFT120 ms
tokens (in / out)142 / 218
cost (header)$0.0008
callbacks firedlangfuse, datadog
90d retentionmetadata onlyPII-redact off
Default log retention
90 days

Financial records retained indefinitely

Cost source
x-nemo-request-cost

Provider header — never reconstructed

Latency percentiles
p50 · p95 · p99

Per model, per key, per org

PII masking
Optional

Per-org policy: zero / meta / full / redacted

The request log

Successes, rate-limits, cache hits, guardrail blocks — one stream.

Searchable, filterable, expandable per row. Logged async — zero latency added to the request path.

request_log · streaming
12:04:31.204gemini-2.5-flash200langfuse · datadog
12:04:30.871gemini-2.5-pro200s3 archive
12:04:30.412gemini-2.5-flash200cache hit
12:04:29.960gemini-2.5-flash429rate-limit · retry-after 4s
12:04:29.512imagen-4.0200image · vision tag
12:04:28.733gemini-2.5-pro403guardrail_blocked · injection
Log flow

Provider → Backend → Callbacks (async)

Nemo Router captures the provider cost directly — no extra hop where the cost header can be lost or rewritten. Logs are recorded, callbacks fan out async with a retry queue.

Async log path

  1. Provider

    Vertex / Anthropic / OpenAI

    Returns x-nemo-request-cost header — the source of truth.

  2. Nemo Intelligent Proxy Router

    Routing engine

    Computes cost, attaches metrics, emits log event.

  3. Nemo Backend

    Nemo Router

    Records request_log, fans out to enabled callbacks async.

  4. Callbacks

    Langfuse · Datadog · S3 · Slack

    Fire-and-forget delivery with retry queue.

Cost truth

Provider cost header is the source of truth

Cost integrity

One number, four surfaces, zero drift

We never compute cost ourselves. The same x-nemo-request-cost value lands in the request_log row, the credit ledger, every active callback, and the analytics rollup — one upstream value, four downstream consumers, no recomputation. Missing-header rows are flagged for reconcile, never silently zeroed.

  • Source: provider response header (x-nemo-request-cost)
  • Sinks: request_log, credit ledger, callbacks, analytics
  • Daily ledger parity check: sum(transactions) == balance
  • Zero-cost settlements are the canonical revenue-leak signal
cost · last 60s

Cost-header integrity

Requests with cost header8 421 / 8 421
Missing-header rows0
Settled to ledger8 421
Ledger drift (24h)$0.00
Callbacks firedlangfuse · datadog · s3
Cost sourcex-nemo-request-cost
header truthno recomputationno drift
Full reference — callbacks, alerts, data policy, latency metrics
Request logs
Every call captured with model, status, latency, cost, tokens — and full prompt/response if your data policy allows. Per-row expand, filter by model/status/time/key/team. 90-day retention default; longer on Enterprise.
Logging callbacks
Langfuse (traces + spans + generations), Datadog (metrics + correlation IDs), S3 (raw JSON archive), Slack (real-time event feed), and custom HTTPS webhooks with signed payloads. One toggle each, async, fire-and-forget with retry queue.
Latency metrics
p50 / p95 / p99 + max per model, key, team, org — time-to-first-token and total latency tracked separately, streaming-aware (TTFT measured at first SSE event). CSV export for long-tail diagnosis.
8 alert types
LLM errors, budget thresholds, provider outages, latency spikes, rate-limit hits, guardrail blocks, key expirations, spend anomalies. Multi-channel delivery: email + Slack + Teams + webhook, with per-org thresholds and hysteresis.
Data policy — 4 levels
Zero (billing-essential only), metadata-only (default: model, tokens, cost, latency, status), full (complete prompt + response), or PII-redacted (full with Presidio masking pre-storage). Switch any time per org; applies immediately.
Async — zero added latency
Log ingestion happens after the response returns (< 100 ms to the in-product viewer). Failed callbacks never affect request success. The cost-header passthrough is the only synchronous invariant.
FAQ

Common observability questions

90-day retention · 4 callbacks · 8 alerts

See every request — without DIY observability infrastructure

Sign up, enable a callback or two, watch the data flow into your existing stack. No agents to install, no schema to invent.