You.com launches Inference Router with 12 open-weight models and 99.9% uptime SLA
You.com introduced the Inference Router, a managed API that aggregates twelve open‑weight models behind a single OpenAI‑compatible endpoint. The service guarantees a minimum 99.9% uptime SLA, zero data retention for prompts and outputs, and 100% US hosting with server‑side web search. It operates on a pay‑as‑you‑go basis with no platform fee, and each model has a published per‑token price.
Key points
- Inference Router offers 12 open-weight models via a single OpenAI-compatible endpoint with 99.9% uptime SLA.
- Prices are per‑million‑token, e.g., Kimi K3 costs $2.85 input / $14.25 output, Qwen3.8 Max $1.85 / $5.55.
- Zero data retention policy stores only metadata; requests first hit You.com Inference Direct then fail over to US‑hosted partners.
The model lineup includes Kimi K3 (2.8 T parameters, $2.85 input / $14.25 output per 1M tokens), Qwen3.8 Max (2.4 T MoE, $1.85 / $5.55), GLM‑5.3 ($1.35 / $4.25), DeepSeek V4.1 Flash ($0.30 / $1.20), Mercury 3 ($0.10 / $0.35) and GPT‑OSS 120B ($0.097 / $0.73). Requests first hit You.com’s own Inference Direct and fail over to vetted US‑hosted partners such as Parasail, Wafer, Alibaba Cloud, Meta and Inception. Benchmarks reported by You.com claim cost advantages over frontier models, with GLM‑5.3 plus search scoring 86.53% at $0.0485 per question.
Model pages: Kimi K3 → · GLM 5.3 → · Mercury 3 →
You.com Launches Inference Router: 12 Open-Weight Models With 99.9% Uptime SLA
MarkTechPost · 23 October 2026
Loading the full article…
This text was published by MarkTechPost and written by Asif Razzaq. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Google Cloud launches Agent Compute Engine for AI agents · 1 src
- Microsoft says its AI diagnostic system outperforms doctors on complex cases · 11 src
- Microsoft says Storm-0940 used AI-driven ARTEX framework in attacks · 13 src
- Anthropic releases always-on agent Claude Duet for Pro/Max users · 2 src
- Perplexity releases Decider for Mac to run pplx-decider-flash-v1.2 locally · 1 src
Comments
via GitHub Discussions