$5 free credits · no card required · 60-second setup

Cut your LLM bill 40-70%. Auditable to the token.

One line change to your OpenAI base URL. We semantically cache, route to the cheapest capable model, and price every request against a versioned book. Your provider keys, your data, your savings.

Drop-in for OpenAI & Anthropic SDKs Bring your own provider keys No prompt storage by default SOC 2 controls in place
↓ try it now, no signup ↓
terminal · drop-in compatible
# Anonymous demo — no API key, no signup, 8 calls/hour per IP
curl https://tokenlens.co.in/api/public/v1/demo \
  -H "Content-Type: application/json" \
  -d '{"messages":[{"role":"user","content":"explain semantic caching in one line"}]}'

# Production — same OpenAI-compatible contract, your provider keys
curl https://tokenlens.co.in/api/public/v1/chat/completions \
  -H "Authorization: Bearer $TOKENLENS_KEY" \
  -d '{"model":"auto","messages":[{"role":"user","content":"hi"}]}'
Requests routed (7d)
Models tracked live
Avg semantic cache hit
Public model index
Live
Try it now — no signup

Run a real call. See your savings.

Hit the public demo endpoint with your own prompt. We use the actual provider token count to size your monthly savings — no estimation.

Live demo · gemini-2.5-flash-lite · 8 free calls/hr
Estimated monthly spend
$13,125$3,617
You save with TokenLens
$9,508/ month (72%)
$114,093 per year
Compare savings across providers
Same workload, three baselines — click a row to set it as your default.
50,000 req/day · 1500500 tok
Baseline modelMonthly spendWith TokenLensYou save%
GPT-4o
OpenAI
$13,125$3,617$9,50872%
Claude Sonnet 4
Anthropic
$18,000$4,885$13,11573%
Gemini 2.5 Pro
Google
$10,313$2,886$7,42772%
Cache hit 35% · 60% routed to Gemini Flash-Lite. Adjust the sliders above to see the comparison update live.
How it works

Live in 10 minutes, not 10 weeks

One config change. Your provider keys stay yours. We never train on your data.

01

Point to TokenLens

Swap your OpenAI or Anthropic base URL. No SDK rewrite, no prompt changes — your existing code keeps working.

baseURL: 'https://tokenlens.co.in/api/public/v1'
02

We govern every request

Each call is matched against the semantic cache, scored against routing policy, redacted for PII, and forwarded to the cheapest capable model.

cache · route · redact · forward
03

Observe, attribute, forecast

Live stream every request, attribute spend per team/prompt, forecast next-month cost, and run evals — all from one console.

/live · /cost-attribution · /forecast · /evals
Developer platform

Drop-in SDKs and a full Management API

Native Node and Python packages that extend the official OpenAI and Anthropic clients. A REST API for provisioning keys, budgets and policies from Terraform, Helm or your CI.

  • @tokenlens/sdk (Node) & tokenlens (Python) — extend OpenAI/Anthropic clients
  • REST: GET / POST / PATCH / DELETE on /api/public/v1/admin/keys
  • Terraform & Helm snippets for declarative key + policy management
  • OpenAI-compatible /chat/completions, /messages, /embeddings, /models
node · openai-compatible
import OpenAI from "@tokenlens/sdk/openai";

const ai = new OpenAI({
  apiKey: process.env.TOKENLENS_KEY,
  // baseURL is already tokenlens.co.in/api/public/v1
});

const res = await ai.chat.completions.create({
  model: "gpt-4o-mini",       // routed → cheapest capable
  messages: [{ role: "user", content: "summarize this PR" }],
});

// usage, cache verdict & route decision exposed on res._tokenlens
console.log(res._tokenlens.cache_hit, res._tokenlens.routed_to);
How we count tokens

Every number is auditable

We don't estimate your bill — we record the provider's own usage payload, price it against a dated book, and re-verify it on a schedule.

Provider returns exact usage

Every OpenAI, Anthropic and Gemini response includes a usage object with prompt_tokens and completion_tokens. We record it byte-for-byte — no estimation.

token_source = exact

Priced against a versioned book

Costs come from model_price_history, snapshotted at the moment of the request. Old rows keep their historical price even when providers re-price.

price_at(model, created_at)

Reconciled hourly, automatically

A scheduled job re-verifies every request from the last 7 days against the price book and rolls up per-day savings — dashboards never drift.

cron · 15 * * * *

Open any request in /live → Inspect to see the raw provider usage payload that produced the number.

Enterprise-grade

Built for the things procurement asks about

PII redaction

Localized regex engine strips emails, phones, Aadhaar/PAN, card numbers before the prompt leaves your tenant.

Per-key budgets

Daily and monthly USD caps enforced at the gateway — keys auto-throttle when they hit the line.

Region restriction

Pin a key to specific provider regions for data-residency compliance.

Soft-revoke audit

DELETE never destroys — keys are soft-revoked with timestamp for forensic replay.

RBAC

Admin role enforced via a separate user_roles table and a SECURITY DEFINER has_role() function.

Versioned price book

Costs snapshotted at request time so historical analytics never drift.

Pricing

Pay for value, not tokens

Start free. Upgrade when your usage grows.

Starter
$0

$5 free credits + $50/mo gateway spend. No card.

  • $5 free credits, no card required
  • $50/mo gateway spend included
  • 1 workspace
  • OpenAI-compatible gateway
  • Semantic cache + Live stream
  • Governance Marketplace access
  • Community support
Most popular
Growth
$499/mo

For scaling AI products.

  • 5 workspaces
  • Smart routing & evals
  • Cost attribution & forecast
  • Governance policies + PII
  • Management API + Terraform
  • Email & Slack support
Enterprise
Custom

For high-volume orgs.

  • Unlimited workspaces
  • Private deployment / VPC
  • SSO / SAML, RBAC
  • Open-core self-host option
  • Custom DPA
  • Dedicated support

Ship your LLM control plane today

Free to start. Bring your own provider keys. See your first auditable cost report in minutes.