share it with your agent: https://t.co/4cqKbMT4H1
OpenRouter 出了个 cookbook，教你把文档丢给 agent，让它自己学会调 OpenRouter 的接口，搞自动化的可以看看。
OpenRouter 在 X 上分享了一篇 cookbook 教程，主题是如何把 OpenRouter 的文档交给智能体使用。教程托管在 openrouter.ai/docs/cookbook 页面，演示让 agent 读取文档后自动调用 OpenRouter 的模型接口。该推文目前获得 3 次点赞，浏览量约 632。
share it with your agent: https://t.co/4cqKbMT4H1
share it with your agent: openrouter.ai/docs/cookbook/… 💬 0 🔄 0 ❤️ 3 👀 632 📊 1 ⚡
Cache hit rates rising from the mid-60s to 89% means real savings on API bills even when model prices stay flat, since repeated context is served cheaper. Teams running agentic workflows with long, repeated system prompts should compare cache rates across providers when routing traffic. OpenRouter's routing data offers a practical benchmark for that cost comparison.
腾讯把 Hy4 接进了 OpenClaw，1M 上下文加视觉，做长任务智能体的可以试试，走 OpenRouter 就能用上。
OpenRouter 的数据挺有意思：DeepSeek 官方只接到不到两成的自家流量，Novita 等十几家第三方都在分这块蛋糕。
Perplexity 的 decider 模型三周内流量涨到 Jev 的十分之一，OpenRouter 数据能直接查，可以看看这匹黑马。
Using one shared embedding space lets teams trade off cost and quality per workload without re-embedding an entire index when they switch models. Search and RAG engineers can index corpora once with Pro and serve high-traffic queries on Fast. Compared with single-tier embedding offerings from OpenAI or Voyage, this two-tier setup reduces operational coupling between indexing and serving.
Listing Embed 5 and Rerank 5 on OpenRouter means teams can combine embedding and reranking with models from other providers under one bill, simplifying vendor management for RAG pipelines. Developers evaluating retrieval stacks can benchmark Cohere's models against alternatives like Voyage or Jina without new contracts. Pricing follows OpenRouter's existing Pro and Fast tier structure.
