You.com's Inference Router is an OpenAI-compatible API that delivers enterprise-grade inference for open-weight models such as Kimi K3, GLM 5.3, DeepSeek V4.1 Flash, Qwen3.8 Flash, Muse Spark 1.3 and Mercury 3. It provides a 99.9% uptime SLA with service credits, 100% US hosting, zero data retention, built-in web search on the same server, pay-as-you-go pricing with no platform fee, and automatic failover from You.com capacity to partner providers.
You.com Inference Router provides access to language models through OpenAI-compatible and Anthropic-compatible API endpoints, using one base URL and API key. Applications can list available models, send requests, and stream responses through either endpoint. Requests can also declare web-search or page-fetch tools, allowing the router to retrieve web information and return the sources used. The service supports existing OpenAI and Anthropic SDKs with a base-URL and credential change. You.com describes the product as serving production workloads with its own inference capacity and automatic failover to partner providers.
