You.com launches Inference Router for 12 open-weight models

The OpenAI-compatible API routes across 12 models, from GPT-OSS 120B (125K context) to Kimi K3 and Qwen3.8 Max (1M context), with a 99.9% uptime SLA, zero data retention and 100% US hosting. Pay-as-you-go with no platform fee; Kimi K3 runs $2.85/$14.25 per token, 5% under Together AI.