OpenRouter
The unified interface for LLMs
OpenRouter is an OpenAI-compatible API and routing layer that provides one interface to hundreds of models across many providers. It adds fallbacks, distributed reliability, pricing controls, rankings, and data-policy controls for teams routing AI traffic.
Recent stories
Nous said Hermes became the top coding app on OpenRouter while shipping an OpenClaw migration patch, Telegram agent-to-agent messaging, and new memory controls. If you run long-lived agents, watch the migration path and memory settings before moving chats or skills hubs.
Z.ai released GLM-5.1, a 744B open model built for long-horizon agentic coding and ranked first among open systems on SWE-Bench Pro. Day-0 support in OpenRouter, Ollama, SGLang, vLLM, OpenCode, and local quantization paths makes it ready to test in existing stacks.
OpenRouter said Qwen3.6-Plus became its first model to exceed about 1.4 trillion tokens in a day, and Qwen said the model also moved to No. 1 on the service. The milestone adds a concrete deployment signal beyond benchmark scores and preview availability, so track usage data alongside evals.
Z.ai released GLM-5-Turbo as a faster GLM-5 variant for OpenClaw-style tool use, with 202K context, OpenRouter access, and higher off-peak limits. Try it as a cheaper speed tier for agent workflows, but benchmark completion quality on your own tasks before wider use.
NVIDIA released Nemotron 3 Super, a 120B open model with 12B active parameters and a 1M-token window, on OpenRouter with free access. Evaluate it for low-cost agent backends, especially if you need local or self-hosted deployment options.