# Metrion

## Docs

- [Plans & Limits](https://metrion.mintlify.app/account/plans.md): Compare Free and Pro plans, understand usage limits, and learn how to upgrade.
- [Security](https://metrion.mintlify.app/account/security.md): How Metrion protects your API keys, isolates your data, and complies with GDPR.
- [Settings](https://metrion.mintlify.app/account/settings.md): Configure your Metrion account, manage your API token, view provider keys, and control billing and alerts.
- [Alert Types](https://metrion.mintlify.app/alerts/alert-types.md): Reference for the four alert types available in Metrion.
- [Alerts](https://metrion.mintlify.app/alerts/overview.md): Get notified when your AI usage crosses defined thresholds.
- [AI Insights](https://metrion.mintlify.app/dashboard/ai-insights.md): AI-generated recommendations to optimize your usage
- [Request Logs](https://metrion.mintlify.app/dashboard/logs.md): Browse and export your individual AI requests
- [Dashboard Overview](https://metrion.mintlify.app/dashboard/overview.md): Understanding your AI usage at a glance
- [How It Works](https://metrion.mintlify.app/how-it-works.md): Understand Metrion's proxy architecture, authentication modes, and what gets recorded per request.
- [Anthropic](https://metrion.mintlify.app/integration/anthropic.md): Route your Anthropic Claude requests through Metrion to track token usage, costs, and latency — with a one-line SDK change.
- [Response Cache](https://metrion.mintlify.app/integration/cache.md): Cache identical AI responses to eliminate redundant provider calls — zero tokens, zero cost, ~80ms response time.
- [Gemini](https://metrion.mintlify.app/integration/gemini.md): Route your Google Gemini requests through Metrion using the OpenAI-compatible SDK — with a one-line change.
- [Grok](https://metrion.mintlify.app/integration/grok.md): Route your xAI Grok requests through Metrion using the OpenAI-compatible SDK — with a one-line change.
- [Mistral](https://metrion.mintlify.app/integration/mistral.md): Route your Mistral AI requests through Metrion using the OpenAI-compatible SDK — with a one-line change.
- [OpenAI](https://metrion.mintlify.app/integration/openai.md): Route your OpenAI requests through Metrion to track token usage, costs, and latency — with a one-line SDK change.
- [Introduction](https://metrion.mintlify.app/introduction.md): What Metrion is, who it's for, and why it's different from calling AI providers directly.
- [Quick Start](https://metrion.mintlify.app/quickstart.md): Get your first tracked AI request in under five minutes.
- [Authentication](https://metrion.mintlify.app/reference/authentication.md): How to authenticate your requests with Metrion.
- [Error Codes](https://metrion.mintlify.app/reference/error-codes.md): HTTP error codes returned by the Metrion proxy.
- [FAQ](https://metrion.mintlify.app/reference/faq.md): Common questions about using Metrion.
- [Request Headers](https://metrion.mintlify.app/reference/headers.md): Optional and required headers for Metrion proxy requests.
- [Proxy Endpoints](https://metrion.mintlify.app/reference/proxy-endpoints.md): Complete reference for Metrion's proxy endpoints.