OpenRouter

Stay up to date with the latest news, updates, and posts from OpenRouter.

Join a small team working on big problems. We are building the best tools to help developers ship AI products.

Transparent pricing for OpenRouter. Pay only for what you use with access to 500+ AI models. Free, Standard, Business, and Enterprise plans available.

Compare AI models by key metrics including benchmarks, price, context length, and other model features. View detailed stats for any model such as latency, uptime, and throughput.

Compare Qwen3.7 Flash from Qwen and Qwen3.7 Max from Qwen on key metrics including benchmarks, price, context length, and other model features.

Compare Qwen3.7 Flash from Qwen and Qwen3.7 Plus from Qwen on key metrics including benchmarks, price, context length, and other model features.

Compare Qwen3.8 2.4T A95B from Qwen and Qwen3.8 Max (0902) from Qwen on key metrics including benchmarks, price, context length, and other model features.

OpenRouter provides developers with seamless access to 500+ AI models through a single API. Backed by leading investors and trusted by millions.

The unified interface for every model. Find the best models & prices for your prompts

How OpenRouter collects, uses, discloses, and protects your personal data.

End User License Agreement for OpenRouter Stealth Program models, covering access, use, data training, and acceptable use policies.

Supplemental terms for individual Stealth Program models on OpenRouter, as required by their respective providers.

The terms and conditions governing your use of OpenRouter and its services.

The unified interface for every model. Find the best models & prices for your prompts

Taiwan-based GMI Cloud raises a $223 million Series B led by ARCHIV and secures a $440 million credit facility from ChinaTrust Commercial Bank to expand its GPU infrastructure globally. Its Kubernetes-based Cluster Engine provisions GPU clusters in seconds, and its platform offers Nvidia H100, H200 and Vera Rubin GPUs across data centers in Taiwan, Thailand and Malaysia. The company says realized ARR has grown fivefold in the past year, contracted ARR is set to grow tenfold from its December 2025 level by year-end, and its inference platform processes more than 4 trillion tokens weekly.

Sep 2026 · SiliconAngleNews article

Rabbit unveils OS3, a cloud-based personal AI agent that connects to users’ computers and other devices through an installed Rabbit agent. OS3 runs on Windows, macOS and Linux, supports up to five machines, and can use user-provided model keys or local models, with model switching that preserves context, memory and skills. It works through chat, voice, web and a paired Telegram bot; Rabbit says it follows user instructions and requires consent for sensitive actions.

Sep 2026 · SiliconAngleNews article

Xiaomi releases and open-sources its MiMo-V2.6 family, comprising Pro and Flash multimodal models that support text, image, video and audio with 1-million-token context windows. The company says Pro scores 46.32 on the Artificial Analysis Intelligence Index and posts competitive results on several agentic benchmarks, while remaining behind leading proprietary models on aggregate measures. Xiaomi maintains MiMo-V2.5 API pricing, and says the Pro-UltraSpeed variant delivers up to 20 times faster output at the same quality.

Sep 2026 · SiliconAngleNews article

Peterson, Cisco Systems Inc.’s vice president of product management for Secure WAN, argues that enterprise AI needs dynamic model routing grounded in context, policy, visibility and controls. He compares model routing to SD-WAN, which steers traffic using application and network signals, and says model selection should account for task requirements, performance, cost, privacy and current conditions. AI workflows spanning branches, clouds, SaaS, data stores and services make adaptive routing especially important at the edge.

Sep 2026 · SiliconAngleNews article