You.com Launches Inference Router: 12 Open-Weight Models With a 99.9% Uptime SLA
You.com has launched Inference Router, a managed API for running open-weight models in production. The You.com Inference Router is an OpenAI-compatible service that routes requests across 12 live models. It bundles a 99.9% minimum uptime SLA with zero data retention (ZDR), adds 100% US hosting and server-side web search, and bills on a pay-as-you-go basis with no platform fee.
TL;DR
- Scale: 12 live models, ranging from GPT-OSS 120B (125K context) to Kimi K3 and Qwen3.8 Max (1M context). Kimi K3 is a 2.8T-parameter model; Qwen3.8 Max is a 2.4T Mixture-of-Experts (MoE) model.
- Managed operation: Requests hit You.com Inference Direct first, then fail over to US-hosted partners. There are no GPUs to manage.
- Performance: In You.com's LiveNewsBench run, open-weight models combined with You.com search matched frontier models at lower cost.
- Best result: GLM-5.3 with You.com search scored 86.53%, at $0.0485 per question versus $0.0920 for Claude Sonnet 5.5 (self-reported).
- Worst result: Per-token prices sit near market rates. Kimi K3 is $2.85/$14.25, only 5% below Together AI's $3.00/$15.00.
What Is the You.com Inference Router?
It is a single API for many open-weight models. The endpoint is https://api.you.com, and it ships with an OpenAI-compatible interface, so existing OpenAI SDK integrations can be redirected with minimal code changes.
via MarkTechPost