# Tokonomics

> AI cost metering proxy for any stack. Track every LLM API call, set budget alerts, and control spending across 9+ providers.

Tokonomics is a SaaS API proxy that sits between your application and LLM providers. It intercepts every API call, records token usage, calculates cost in real-time, and enforces budget controls. Language-agnostic: works with any HTTP client (PHP, Python, Node.js, Go, Ruby, etc.).

## Docs

- [API Documentation](https://tokonomics.ca/docs): Full API reference with code examples
- [Pricing](https://tokonomics.ca/pricing): Free ($0/mo, 100 calls) and Pro ($49/mo, unlimited)
- [Blog](https://tokonomics.ca/blog): 44 articles on LLM cost management
- [Status](https://tokonomics.ca/status): Service uptime and incident history
- [Changelog](https://tokonomics.ca/changelog): Product updates and releases

## API

- POST /proxy/{provider}/{path} — Forward LLM requests and record usage
- GET /analytics/summary — Current month spend and budget percentage
- GET /analytics/daily?days=30 — Daily spend for last N days
- GET /analytics/by-tag?key=team — Spend grouped by custom tag
- GET /analytics/events?limit=50 — Paginated raw usage events
- GET /health — Health check (no auth required)

Authentication: Bearer token with `mk_` prefix in Authorization header.

## Supported Providers

OpenAI, Anthropic, DeepSeek, Google Gemini, Mistral, Groq, Together AI, Cohere, xAI, and any OpenAI-compatible API.

## Optional

Tokonomics provides real-time cost tracking with 8-decimal USD precision, budget alerts via email/Slack/Teams/webhook, hard spending caps that block requests when budget is exceeded, per-feature cost attribution via custom tags, BYOK (Bring Your Own Keys) with AES-256 encryption, and rate limiting per API key.

Free plan: 100 API calls/month, 1 seat, 30-day data retention.
Pro plan ($49/month): Unlimited calls, 5 seats, 90-day retention, hard caps, unlimited alerts.

Contact: hello@tokonomics.ca