# LLM

Configure providers, route between models, cache responses, and track cost.

## Pages

- [Providers](providers.md) — every wired `LLMClientFactory` client and how to add your own.
- [Routing](routing.md) — Pick the right model per request (size, cost, capability).
- [External Configuration](configuration-sources.md) — Change an agent's provider, model or tuning from a JSON file or the environment, without recompiling.
- [Caching](caching.md) — Prompt cache, response cache.
- [Cost Tracking](cost-tracking.md) — Per-agent and per-session cost accounting.
- [Observability](observability.md) — Capture every LLM call as a typed `LLMCallLog` event with prompt, response, usage, cost, and streaming timing.
- [Audio](audio.md) — Speech-to-text and text-to-speech.
- [Advanced](advanced.md) — Request hooks, custom transports, rate limiting.