You.com has launched the Inference Router, a new API service designed to simplify the deployment of open-weight AI models. This service offers compatibility with OpenAI and Anthropic APIs, routing requests to a selection of 12 different models, including large parameter models like Kimi K3 and Qwen3.8 Max, with context windows up to 1 million tokens. The Inference Router guarantees a 99.9% uptime SLA, zero data retention, and 100% US hosting, addressing common migration hurdles for developers. It also integrates web search capabilities, aiming to provide competitive performance at a lower cost compared to frontier models. AI
IMPACT Simplifies deployment of open-weight models, potentially lowering costs and increasing adoption for developers.
RANK_REASON Product launch of an API service for running open-weight models.
- Alibaba
- Anthropic
- Claude Sonnet 5.5
- DeepSeek V4 Pro
- GLM 5.3
- GPT-OSS 120B
- Inference Router
- Kimi K3
- Moonshot AI
- OpenAI
- Together AI
- You.com
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →