You.com launches Inference Router: one-line switch to open-weight models, up to 75% cheaper
RichardSocher · x · 2026-10-23
You.com founder Richard Socher announced Inference Router, an enterprise inference service for open-weight models: change your base URL in one line and existing OpenAI-compatible code runs on it, with no platform fees.
Key facts:
- Hosts leading open models including Kimi K3 (Moonshot, 1M context, toggleable max-effort thinking), GLM 5.3 (Z.ai), DeepSeek V4.1 Flash, Qwen3.8 Flash, and Meta's Muse Spark 1.3
- Guarantees a 99.9% minimum uptime SLA, zero data retention (ZDR), and 100% U.S.-hosted models
- Claims up to 75% lower inference costs; customer quotes cite bills cut in half, better agent latency, and less downtime than closed-weight APIs
- Positioning: on-demand inference routing for enterprises running long-horizon agents and high-volume workloads
Related event: You.com Launches Enterprise Inference Router with 99.9% SLA(5 posts)→
More from Infra
- Bloom Energy Q3 revenue hits $1.24B, up 138% YoY, raises FY26 guidance to $4.4-4.6B — Beth_Kindig · 2026-10-23
- 1M+ PHP services patched in 24h, but ~40M still exposed to PHP2Shell CVEs — FanaHOVA · 2026-10-23
- Trader dismisses AI circular financing theory: every new megawatt booked at rising spot prices — JOBhakdi · 2026-10-23
- Rumor: New Architectures Could Cut Cerebras K3 Wafer Needs From 60 to 10 — bookwormengr · 2026-10-23
- Nvidia plunges 7.21% to $212.31 in a day, still holding a $5.2T market cap — michalmalewicz · 2026-10-23
- Serverless Is a Billing Model: How to Price Stateful Compute by Usage — s4chinraja · 2026-10-23