Skip to main content
Muxx is an AI gateway and observability platform that sits between your application and LLM providers. It logs every request, tracks costs, measures latency, and provides a dashboard to understand your AI usage.

​
Why Muxx?

Building AI-powered applications is exciting, but running them in production is challenging:
  • Cost visibility - LLM API costs can spiral quickly. Muxx tracks every token and dollar.
  • Debugging - When something goes wrong, you need to see the full request/response. Muxx logs everything.
  • Performance - Response caching reduces latency and costs for repeated queries.
  • Reliability - Rate limiting and spend caps protect your budget and prevent abuse.

​
Three Integration Modes

Muxx offers flexibility in how you integrate:

Gateway Only

Just change your base URL. Get logging, caching, and rate limiting instantly with zero code changes.

SDK Only

Wrap your LLM client for deep tracing with traces and spans. Direct calls to providers with zero latency impact.

SDK + Gateway

Best of both worlds. SDK tracing combined with gateway caching and rate limiting.

​
Supported Providers

Muxx currently supports:
  • OpenAI - GPT-4o, GPT-4o-mini, GPT-4-turbo, and more
  • Anthropic - Claude 3.5 Sonnet, Claude 3.5 Haiku, and more
  • Google - Gemini Pro, Gemini Flash, and more
Coming soon: Mistral, Groq, Azure OpenAI, AWS Bedrock.

​
Next Steps

Quickstart

Get up and running in under 5 minutes

Concepts

Understand key concepts like traces, spans, and generations