Infermux v0.1.0 — an inference router for managing and routing requests across multiple AI/LLM providers.
Features
- Provider Registry — Register and manage multiple inference providers with configurable endpoints and credentials
- Model Routing — Automatically route inference requests to the appropriate provider based on model identifiers
- Token & Cost Tracking — Track token usage and estimated costs per request across providers
- Trace Integration — Built-in tracing support via mist-go for observability and debugging
- HTTP API — RESTful API server for inference routing, provider management, and health checks
- CLI — Command-line interface for starting the server and managing configuration