v1.0.0 · live

Every call.
Every model.
Logged.

Drop-in SDK that traces every LLM call across OpenAI, Anthropic, and Gemini. Token spend, latency, prompt versions — two lines of code, then you're done.

Read the docs ↗View on GitHub ↗

two lines

Wrap your client. That's it.

app/server.ts

// 1. init once at boot
import { init, wrapOpenAI } from 'tokentrace-sdk';
init({ apiKey: process.env.TOKENTRACE_KEY });

// 2. wrap your provider client
const openai = wrapOpenAI(new OpenAI());

// every call is now traced — streaming and non-streaming
const res = await openai.chat.completions.create({ ... });

features · 03

What the dashboard tells you.

spend

$2,418/24h

↓ 12.4%

Catch cost regressions before they ship.

Token spend tracked per model, per prompt version, per route. Anomalies surface within 60s.

latency

84ms p50

— stable

Find the prompt that just got slow.

Histogram + p50/p95/p99 per model. Drill into individual traces in two clicks.

promptsTeam · coming soon

142versions

↑ 3 today

Diff prompts the way you diff code.

Every prompt is versioned automatically. Side-by-side diff with cost and quality deltas.

pricing

First project free. Flat fee per project above.

No per-seat tax. No “contact sales” tier. Pay per project, not per person.

Free100k traces / month

$0first project

✓100k traces / month
✓7 days retention
✓All providers
✓Anomaly alerts
✓Community Discord

Get an API key

Proup to 10M traces / month

$49/ project / month

✓10M traces / month
✓90 days retention
✓Prompt diff + version history
✓Slack / PagerDuty alerts
✓SSO + audit log
✓Priority email

Start 14-day trial

Additional projects from $5 / month (100k traces) or $49 / month (10M traces). Above 10M, $4 per additional 1M. We email you at 80%.

Every call.Every model.Logged.