# Tokonomics

## Docs

- [GET /analytics/by-tag — AI Spend Grouped by Tag Key](https://tokonomics.mintlify.app/api-reference/analytics-by-tag.md): Returns AI spend and request counts grouped by a custom tag key — such as team, feature, or tenant — over a week, month, or quarter.
- [GET /analytics/daily — Daily Spend Trend Breakdown](https://tokonomics.mintlify.app/api-reference/analytics-daily.md): Returns per-day AI spend totals and request counts for up to 90 days, helping you track trends and detect anomalies across your billing period.
- [GET /analytics/events — Paginated Raw Usage Events](https://tokonomics.mintlify.app/api-reference/analytics-events.md): Returns paginated raw usage event records with full token counts, cost, latency, model, provider, and custom tags for every LLM call.
- [GET /analytics/summary — Current Month Spend Summary](https://tokonomics.mintlify.app/api-reference/analytics-summary.md): Returns the current-month total spend in USD, budget utilization percentage, and a per-model cost breakdown for your Tokonomics account.
- [Tokonomics API Reference — Overview and Authentication](https://tokonomics.mintlify.app/api-reference/overview.md): Base URL, authentication, rate limits, and error codes for the Tokonomics REST API. Everything you need before making your first request.
- [POST /proxy/{provider}/{path} — Proxy LLM Requests](https://tokonomics.mintlify.app/api-reference/proxy.md): Proxy LLM requests through Tokonomics for automatic cost metering. Supports OpenAI, Anthropic, DeepSeek, Gemini, Mistral, xAI, Cohere, Groq, and Together.
- [Authenticate Your Tokonomics API Key on Every Request](https://tokonomics.mintlify.app/authentication.md): Tokonomics uses API keys for authentication. Every request must include your mk_ key in the Authorization header as a Bearer token.
- [Set Budget Alerts and Hard Spending Caps in Tokonomics](https://tokonomics.mintlify.app/concepts/budgets.md): Set monthly budget thresholds so Tokonomics alerts you at 50%, 80%, and 100% of spend — or enforces hard caps on Pro to block overage.
- [How Tokonomics Tracks and Calculates LLM Costs in Real Time](https://tokonomics.mintlify.app/concepts/cost-tracking.md): Tokonomics extracts token counts and calculates costs in real time from every LLM response, giving you exact USD spend with 8-decimal precision.
- [How the Tokonomics Proxy Works with Your LLM Provider](https://tokonomics.mintlify.app/concepts/proxy.md): Tokonomics is a transparent pass-through proxy between your app and any LLM provider, forwarding requests and streaming responses with under 1ms overhead.
- [Tag LLM Requests for Cost Attribution in Tokonomics](https://tokonomics.mintlify.app/concepts/tagging.md): Attach custom tags to every LLM call so you can break down AI spend by team, feature, environment, or any dimension your business needs.
- [Track Anthropic Claude API Costs with Tokonomics Proxy](https://tokonomics.mintlify.app/guides/anthropic.md): Swap the Anthropic base URL for Tokonomics to track Claude API costs in real time — your request format and streaming stay exactly the same.
- [Configure AI Budget Alerts and Hard Caps in Tokonomics](https://tokonomics.mintlify.app/guides/budget-alerts.md): Configure Tokonomics to send Slack, Teams, email, or webhook alerts when your AI spend crosses 50%, 80%, or 100% of your monthly budget.
- [Attribute AI Costs to Teams, Features, and Tenants](https://tokonomics.mintlify.app/guides/cost-attribution.md): Use Tokonomics metering headers to tag every LLM call and then query spend broken down by team, feature, environment, or customer tenant.
- [Connect OpenAI to Tokonomics for Automatic Cost Metering](https://tokonomics.mintlify.app/guides/openai.md): Replace the OpenAI base URL with Tokonomics to start tracking GPT-4o, o1, and other OpenAI model costs automatically — no other code changes needed.
- [Connect DeepSeek, Gemini, Mistral, and More to Tokonomics](https://tokonomics.mintlify.app/guides/other-providers.md): Route calls to DeepSeek, Gemini, Mistral, xAI, Cohere, Groq, and Together AI through Tokonomics using the same one-URL-swap pattern.
- [Tokonomics: Budget-First AI Cost Metering and Alerting](https://tokonomics.mintlify.app/introduction.md): Learn how Tokonomics sits between your app and any LLM provider to track token usage, calculate costs, and fire budget alerts automatically.
- [Get Started with Tokonomics: Make Your First Metered Call](https://tokonomics.mintlify.app/quickstart.md): Set up Tokonomics in under five minutes: create a free account, generate your API key, and point your existing LLM client at the proxy.
- [Metering, Tagging, and Rate Limit Headers Reference](https://tokonomics.mintlify.app/reference/metering-headers.md): Reference for all request and response headers Tokonomics adds, strips, or passes through — including tagging headers and rate limit signals.
- [Tokonomics Free and Pro Plans: Features and Limits](https://tokonomics.mintlify.app/reference/plans.md): Compare the Tokonomics Free and Pro plans — from proxy call limits and API key counts to data retention, analytics API access, and hard spending caps.
- [Supported AI Providers, Slugs, and Proxy Endpoints](https://tokonomics.mintlify.app/reference/providers.md): Complete list of LLM providers supported by Tokonomics, including their proxy slugs, upstream base paths, and compatible API formats.