You.com launches Inference Router with 12 open-source models and a 99.9% uptime SLA

AI search company You.com has introduced Inference Router, a managed API service built for running open-source models in production. The product is compatible with the OpenAI API and can route requests across 12 live models. You.com says the service comes with a 99.9% minimum uptime SLA, a zero data retention policy, 100% U.S. hosting, and server-side web search. It uses a pay-as-you-go pricing model and does not charge a platform fee. The company said the integrated models include Kimi K3, Qwen3.8 Max, GLM-5.3, and DeepSeek V4 Pro, all hosted in the United States. Pricing examples listed in the report show Kimi K3 at $2.85 per million input tokens and $14.25 per million output tokens, while Qwen3.8 Max is priced at $1.85 per million input tokens and $5.55 per million output tokens. Requests are first sent to You.com’s own inference infrastructure. If that system goes down or reaches capacity, traffic fails over to vetted partners including Parasail, Wafer, Alibaba Cloud, Meta, and Inception. According to the report, all partners must meet the same zero data retention and U.S. hosting requirements.