AI FinOps, redefined

Understand Every AI Dollar.

Monitor OpenAI, Anthropic, Google, Azure OpenAI, Grok, OpenRouter, Ollama, and every AI provider from one unified platform.

Encrypted credentials Zero-latency ingest 10-minute setup
app.costorah.comLive
This month
$48,392
↓ 18% vs last month
Spend by provider
7-day view
OpenAIAnthropicGoogle
Trusted AI Infrastructure
OpenAIAnthropicGoogle GeminiAzure OpenAIOpenRouterGrokOllama
Live dashboard

See your AI economy in real time.

Every provider, every model, every project — normalized, correlated, and streamed live.

Spend today
$3,284
+4.2%
Requests
1.2M
+11%
Tokens
284M
+6%
Avg latency
612ms
-8%
Anomalies
3
live
Active users
94
+2
Cost forecast
Next 30 days
± 4.1% confidence
Provider mix
This quarter
OpenAI42%
Anthropic28%
Google18%
Other12%
Top models by spend
Last 30 days
Live activity
Streaming events
Live
OpenAIgpt-4o
18,240 tok$0.42
Anthropicclaude-3.5-sonnet
9,120 tok$0.31
Googlegemini-1.5-pro
24,880 tok$0.19
Azuregpt-4o-mini
62,300 tok$0.09
OpenRouterllama-3-70b
3,410 tok$0.02
Platform

Every capability a modern AI team needs.

From ingestion to forecasting — one focused platform for FinOps, platform, and finance teams.

Unified AI Spend
One ledger across every provider, model, project, and team.
Usage Analytics
Token, request, and cost breakdowns down to the endpoint.
Live Monitoring
Streaming metrics with sub-second update latency.
API Keys
Rotate, scope, and revoke provider keys from one vault.
Organizations
Multi-tenant workspaces with clean isolation boundaries.
Projects
Segment spend by product, environment, or customer.
Alerts
Budget and anomaly alerts in your in-app notification center. Email, Slack, and webhooks coming soon.
Budget Tracking
Org, project, provider, and model-level budgets with configurable thresholds.
Forecasting
Trend-based spend projections right on your dashboard.
Cost Optimization
Spot your highest-cost models and providers at a glance — model routing and prompt insights are on the roadmap.
Provider Comparison
Side-by-side spend and usage across every connected provider.
Model Comparison
Compare cost and token usage across every model you use.
Real-time Dashboard
Live KPIs and charts, streamed over WebSocket with a polling fallback.
SDKs
Python and JavaScript/TypeScript today — more languages coming soon.
Webhooks
Coming soon — push cost events to Slack, email, and your own endpoints.
RBAC
Owner, Admin, Member, and Viewer roles with a full audit trail. SSO is on the roadmap.
How it works

Five steps to AI cost clarity.

From first connection to automated forecasts — Costorah is designed to fit into the workflow you already have.

1
Connect AI Providers
API key or OAuth. OpenAI, Anthropic, Google, Azure, OpenRouter, Grok, and Ollama.
2
Collect Usage
Manual or automatic background sync normalizes tokens, requests, and cost.
3
Analyze Costs
Slice by team, project, model, or provider in real time.
4
Spot Waste
See your highest-cost models and providers at a glance.
5
Forecast & Budget
Track spend against configurable budgets, with more automation on the way.
Built for developers

Ship in minutes.
Instrument once.

Python and JavaScript/TypeScript SDKs, a clean REST API, and a CLI. Track every AI call with a single line of code — or ingest server-side with zero client changes.

Python SDK
JavaScript / TypeScript SDK
REST API
CLI
Realtime API
More languages — coming soon
track.py
python
from costorah import Costorah

client = Costorah(api_key="ck_live_...")

response = openai.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello"}],
)

client.track(
    provider="openai",
    model="gpt-4o",
    usage=response.usage,
    project="production",
)
track.ts
typescript
import { Costorah } from "costorah";

const client = new Costorah({ apiKey: process.env.COSTORAH_KEY! });

const res = await openai.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Hello" }],
});

await client.track({
  provider: "openai",
  model: "gpt-4o",
  usage: res.usage,
  project: "production",
});
Security

Enterprise-grade from day one.

Designed with the controls that regulated industries require — and audited to prove it.

RBAC
Granular role-based access control.
Org isolation
Hard tenant boundaries.
Audit logs
Every action, immutable.
Encrypted keys
Provider credentials encrypted at rest, per-connection.
One account system
Single, unified auth across the whole product.
Least data by default
We store usage metadata, not prompts or completions.
Security-first development
Built with modern secure-coding practices.
TLS everywhere
Encrypted in transit, end to end.
Pricing

Simple pricing that scales with you.

Start free today. Team and Enterprise plans with billing are coming soon.

Starter
For solo builders and side projects.
$0forever
  • Up to 1M tokens/mo
  • 3 providers
  • 7-day retention
  • Community support
Start free
Popular
Team
For growing teams shipping AI products.
Coming soon
  • Everything in Free
  • Higher usage limits
  • Longer data retention
  • Priority support
Join the waitlist
Enterprise
For regulated and high-scale organizations.
Coming soon
  • Everything in Team
  • SSO & advanced RBAC
  • Custom retention
  • Dedicated support
Contact sales
FAQ

Everything you might ask.

Which AI providers do you support?

OpenAI, Anthropic, Google Gemini, Azure OpenAI, OpenRouter, Grok, and Ollama today, with more providers on the way.

How fast is setup?

A few minutes. Connect a provider, drop in our Python or JavaScript SDK, and usage starts flowing in.

Does Costorah sit in the request path?

No. We collect usage out-of-band via provider APIs and optional client SDKs, so there's no added latency to your requests.

Can I set budgets and alerts?

Yes. Organization, project, provider, and model-level budgets with configurable thresholds are available today, shown in your in-app notification center. Email, Slack, and webhook delivery are coming soon.

How do you handle sensitive data?

We store usage metadata — tokens, cost, model, timestamps. Prompts and completions are never collected.

Do you offer SSO and RBAC?

Role-based access control (Owner/Admin/Member/Viewer) is available today. SSO is on our roadmap.

What SDKs are available?

Python and JavaScript/TypeScript SDKs are available today. Additional language SDKs are coming soon.

Do you have a free tier?

Yes. The Free plan is free forever, with no credit card required.

Start monitoring AI costs today.

Free forever for individuals and small teams. No credit card required.