X:OpenRouter
@openrouter · X
切换来源
@OpenRouter@openrouterAI 评分4646 
@OpenRouter@openrouterAI 评分1818 了解更多:openrouter.ai/docs/guides/ro…
@OpenRouter@openrouterAI 评分6060 
@OpenRouter@openrouterAI 评分3232 RT @OpenRouter: OpenRouter 上的 Guardrails 是市场上最强大的:为你的 AI 流量提供集中式安全与治理 预算…
@OpenRouter@openrouterAI 评分6262
引用OpenRouter (@OpenRouter)@OpenRouterGuardrails on OpenRouter are the most powerful in the market: centralized security & governance for your AI traffic Budget limits, ZDR, model & provider restrictions, prompt injection defense, and DLP / sensitive info detection, layered into rules you control! 🧵
@OpenRouter@openrouterAI 评分6363 引用MiniMax (official) (@MiniMax_AI)@MiniMax_AIIntroducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities - Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas - MiniMax Sparse Attention scales context to 1M - Natively Multimodal from Step Zero API: platform.minimax.io Token Plan: platform.minimax.io/subscrib… 🚀New! MiniMax Code: code.minimax.io Weights & Tech Report in ~10 Days
@OpenRouter@openrouter精选AI 评分6868 OpenRouter 上线 MiniMax M3,首周提供 50% 折扣,用户可通过 openrouter.ai/minimax/minimax-m3 直接试用。
推荐理由:原文给出 MiniMax M3 在 OpenRouter 的上线入口与首周五折,读者可据此判断接入成本与试用时机。
@OpenRouter@openrouter精选AI 评分7575 
推荐理由:原文列出上下文窗口、编码、智能体和多模态四个方面,读者可据此了解这个开放权重模型的配置取向。
@OpenRouter@openrouter精选AI 评分6767 推荐理由:MiniMax-M3 以 100 万上下文和多模态能力接入 OpenRouter,并给出每百万 token 输入输出定价,便于开发者比较接入成本。
@OpenRouter@openrouterAI 评分77
@OpenRouter@openrouterAI 评分2727 注意:Google Model Armor 和 @LakeraAI Guard 处于 beta 阶段。如需使用请联系我们!
@OpenRouter@openrouterAI 评分2727 更多内容请见我们的博客!openrouter.ai/announcements/…
@OpenRouter@openrouterAI 评分4444 
@OpenRouter@openrouterAI 评分6161 @OpenRouter@openrouterAI 评分4242 5/ 新功能:按请求可观测性 你可以看到发生的一切。每个护栏动作都会记录到你的请求日志中,包含结果、作用范围、触发的具体护栏,以及被拦截内容的详情,一直细化到单次生成。

@OpenRouter@openrouterAI 评分6161 
@OpenRouter@openrouterAI 评分5555 
@OpenRouter@openrouterAI 评分5858 OpenRouter 新增预算限额功能,可按日、周、月设置支出上限并配置重置窗口,超出上限的请求会返回 403,避免单个失控脚本耗尽预算。API key 的预算独立叠加在成员预算之上。

@OpenRouter@openrouterAI 评分6161 
@OpenRouter@openrouterAI 评分5757 
@OpenRouter@openrouterAI 评分5353 引用ComfyUI (@ComfyUI)@ComfyUIComfyUI just added @OpenRouter support. Instead of being locked into a single LLM, you can now access 20+ models directly inside Comfy. More flexibility, less friction, same workflow. Links to the workflows below👇 Video
@OpenRouter@openrouterAI 评分5454 @OpenRouter@openrouterAI 评分5959 
@OpenRouter@openrouter精选AI 评分6969 引用StepFun (@StepFun_ai)@StepFun_ai⚡️ Step 3.7 Flash is here: The new frontier is agent efficiency. #1 ClawEval-1.1 (67.1), #1 SimpleVQA Search (79.2), #2 SWE-PRO (56.3), 95.3 on V* Python. Open weights under Apache 2.0. Built for agentic, coding, search, and multimodal workflows — balancing speed, cost, and reliable execution. - 400 TPS. 198B sparse MoE, ~11B active. 256K context, 3 reasoning levels. - Understands UIs, charts, docs, images — then writes code or calls tools to act on what it sees. - Web + visual search reaches further: more sources, deeper follow-up. - Reliable tool use — less drift, fewer broken toolcalls. 98%+ on τ²-bench across all difficulty levels. - Works with Claude Code, KiloCode, Hermes Agent, OpenClaw, and protocols like MCP. - Runs locally on Mac Studio M4 Max, DGX Spark, AMD AI Max+ 395. GitHub: github.com/stepfun-ai/Step-3… HuggingFace: huggingface.co/stepfun-ai/St… GGUF: huggingface.co/stepfun-ai/St… ModelScope: modelscope.cn/models/stepfun… API: platform.stepfun.ai Blog: static.stepfun.com/blog/step…
推荐理由:从开放权重和速度成本平衡切入 agent 场景,读者可对照其编程与搜索评测及本地部署支持。
@OpenRouter@openrouterAI 评分3838 试试看:openrouter.ai/stepfun/step-3…
@OpenRouter@openrouterAI 评分5252 
@OpenRouter@openrouterAI 评分5050 
@OpenRouter@openrouterAI 评分5353 OpenRouter 发布博客,公布其 Series B 的完整投资方名单,其中包括 amppublic 和 PaceCap,并感谢所有天使投资人的支持。
@OpenRouter@openrouterAI 评分4242 在这里试用 Opus 4.8 Fast Mode:openrouter.ai/anthropic/clau…
@OpenRouter@openrouterAI 评分6262 @OpenRouter@openrouter精选AI 评分7878 
推荐理由:原文给出 Opus 4.8 在智能体编码与推理上的变化,以及快速模式的定价比例,便于对照 4.7 判断升级取舍。
@OpenRouter@openrouterAI 评分00 @OpenRouter@openrouterAI 评分4747 @OpenRouter@openrouterAI 评分3535 @nytimes 独家报道:nytimes.com/2026/05/26/busin…
@OpenRouter@openrouter精选AI 评分6565 
推荐理由:OpenRouter 公布 1.13 亿美元 B 轮融资,并给出周 token 量半年从 5T 增至 25T 的数据,可观察模型调用向生产环境的迁移。
@OpenRouter@openrouterAI 评分4141 OpenRouter 现已在 @warpdotdev 中获得支持!❤️
引用Warp (@warpdotdev)@warpdotdevYou can also connect to inference endpoints that follow the OpenAI Chat Completions API. This includes @OpenRouter, @LiteLLM, @Zai_org, @deepseek_ai, and more. Here's engineer Dagm Assefa showing how to connect to DeepSeek and OpenRouter. Docs: docs.warp.dev/agent-platform… 🔖 Video