Skip to main content
Tokonomics is a budget-first AI cost metering proxy that sits between your application and any LLM provider. Every token you send and receive is counted, priced, and logged in real time — without any changes to your prompts or application logic. Point your existing OpenAI, Anthropic, or other provider SDK at Tokonomics, and you get instant visibility into spend, usage trends, and budget alerts across all your models and teams.

​
Get started

Quick Start

Integrate Tokonomics in 5 minutes — no code changes beyond a single URL swap.

Authentication

Learn how to generate and use your mk_-prefixed API key for every request.

Core Concepts

Understand how the proxy layer works, what gets logged, and how tags flow through.

API Reference

Explore every endpoint, request parameter, and response schema in full detail.

​
How to onboard

1

Create a free account

Sign up at tokonomics.ca. No credit card required. Your free plan includes 100 tracked calls per month so you can explore the dashboard before committing.
2

Generate an API key

In your dashboard, navigate to API Keys and click Create key. Your key starts with mk_ and is shown in plaintext exactly once — copy it to a secure location before closing the dialog.
3

Change your provider base URL

Replace your LLM provider’s base URL with the Tokonomics proxy endpoint:
https://tokonomics.ca/proxy/{provider}/
For example, swap https://api.openai.com/v1 for https://tokonomics.ca/proxy/openai/. Tokonomics forwards every request transparently, captures usage data in the background, and returns the unmodified provider response to your app.

​
Why teams choose Tokonomics

Real-time cost tracking

Every token is priced the moment the response lands. Watch spend accumulate live on your dashboard — broken down by model, provider, and tag.

Budget alerts

Set daily, weekly, or monthly spend caps on any key, team, or project. Tokonomics fires webhook alerts before you blow past your budget.

Tag-based attribution

Attach arbitrary JSON tags to any request with the X-Metering-Tags header. Slice your spend by team, feature, user, or any dimension that matters to you.