https://xantly.com Documentation and updates from Xantly, the AI infrastructure layer for production LLM workloads. en Wed, 15 Apr 2026 17:03:18 GMT https://xantly.com/docs/introduction https://xantly.com/docs/introduction Xantly is the AI infrastructure layer for production LLM workloads. Wed, 15 Apr 2026 17:03:18 GMT https://xantly.com/docs/quickstart https://xantly.com/docs/quickstart Get up and running with Xantly in under 5 minutes. Wed, 15 Apr 2026 17:03:18 GMT https://xantly.com/docs/intelligent-routing https://xantly.com/docs/intelligent-routing How the routing engine analyzes requests and selects the optimal model. Wed, 15 Apr 2026 17:03:18 GMT https://xantly.com/docs/caching-and-performance https://xantly.com/docs/caching-and-performance Multi-layer caching for sub-5ms responses with 62% semantic cache hit rate. Wed, 15 Apr 2026 17:03:18 GMT https://xantly.com/docs/memory-and-context https://xantly.com/docs/memory-and-context Persistent per-organization memory with automatic session detection. Wed, 15 Apr 2026 17:03:18 GMT https://xantly.com/docs/chat-completions https://xantly.com/docs/chat-completions Unified /v1/chat/completions endpoint routing to 10,000+ models. Wed, 15 Apr 2026 17:03:18 GMT https://xantly.com/docs/voice-agents https://xantly.com/docs/voice-agents Build production voice agents 80-90% cheaper with sub-300ms latency. Wed, 15 Apr 2026 17:03:18 GMT https://xantly.com/docs/multi-agent-orchestration https://xantly.com/docs/multi-agent-orchestration Build AI agent pipelines with handoffs, shared memory, and tool use. Wed, 15 Apr 2026 17:03:18 GMT https://xantly.com/docs/cost-optimized-routing https://xantly.com/docs/cost-optimized-routing Automatically route to cheapest model meeting quality thresholds. Wed, 15 Apr 2026 17:03:18 GMT https://xantly.com/docs/benchmark-results https://xantly.com/docs/benchmark-results 252 validations passed — 24/24 industry benchmarks, 10/10 SDK clients. Wed, 15 Apr 2026 17:03:18 GMT https://xantly.com/docs/platform-overview https://xantly.com/docs/platform-overview How Xantly fits in your stack — the AI gateway architecture and request lifecycle. Wed, 15 Apr 2026 17:03:18 GMT https://xantly.com/docs/voice-models https://xantly.com/docs/voice-models 30+ voice models — STT, TTS, Realtime, Audio LLMs, Music generation. Wed, 15 Apr 2026 17:03:18 GMT