OpenRouter
RT @sanmking: @ian_dot_so That’s the bull case for @OpenRouter At a borader level it all starts from evals, measure the performance for d…
中文: RT @sanmking:@ian_dot_so 是 @OpenRouter 的靶点 在波拉德层面，一切都从椭圆形开始，衡量表现为d...
2026-06-08 16:40:47
OpenRouter
This month is, unsurprisingly, Cost Reduction Month. In our data from the last 3 yrs, we commonly see major cost crunches right after the latest breakthrough. We'll ship major features to help you cut inference costs at least once a week, starting with today. Running list 👇
中文: 不出所料，这个月是降低成本的月份。 在过去三年的数据中，我们通常看到在最新突破之后出现重大成本危机。 我们将提供主要功能，帮助您每周至少降低一次推理成本，从今天开始。 跑步列表 👇
2026-06-08 15:49:06
OpenRouter
RT @alexatallah: At OpenRouter, we're moving towards every workstream having: - a source of truth that humans can inspect without promptin…
中文: RT @alexatallah:在 OpenRouter，我们正朝着每个工作流迈进: - 一种人类无需及时就能够检验的真相之源......
2026-06-08 15:45:07
OpenRouter
New server tool: Advisor Let smaller models consult a higher-intelligence "advisor" model. Helps them escape doom loops, and helps you migrate to cheaper models! 🧵 https://twitter.com/OpenRouter/status/2064004944613527730/photo/1
中文: 新服务器工具:顾问 让较小的模型咨询高智能“顾问”模型。 帮助他们摆脱末日循环，并帮助你迁移到更便宜的型号!🧵
2026-06-08 15:21:40
OpenRouter
How do different model providers differ on cache hit rate and effective price? Now you can see real-time cache hit rate and historical traffic from the Pricing tab. Here's Opus 4.8: https://openrouter.ai/anthropic/claude-opus-4.8/pricing https://twitter.com/OpenRouter/status/2063504950429147376/photo/1
中文: 不同型号的供应商在缓存命中率和有效价格上有何不同? 现在，您可以从“定价”选项卡中查看实时缓存命中率和历史流量。以下是 Opus 4.8:
2026-06-07 06:14:52
OpenRouter
RT @Awe_automation: Testing out NVIDIA’s free nemotron ultra via @openrouter https://twitter.com/Awe_automation/status/2063235167691346043/photo/1
中文: RT @Awe_automation:通过 @openrouter 测试 NVIDIA 的免费 nemotron Ultra 网址
2026-06-07 00:42:05
OpenRouter
RT @AlemTuzlak: One of my favorite AI services has truly become @OpenRouter As I develop TanStack AI it has become so easy to just plop in…
中文: RT @AlemTuzlak:我最喜欢的人工智能服务之一，真正变成了@OpenRouter 当我开发TanStack人工智能时，很容易就能将其卷入其中......
2026-06-07 00:41:44
OpenRouter
RT @MicrosoftAI: Fun fact – the images announcing MAI-Image-2.5 - our image generation and editing model were generated by the model itself…
中文: RT @MicrosoftAI:有趣的事实——发布MAI-Image-2.5的图片——我们的图像生成和编辑模型由模型本身生成......
2026-06-06 01:35:20
OpenRouter
Live on OpenRouter: Riverflow 2.5 from @riverflow_ai The first image model with an independent scoring rubric you control to guide its thinking and editing, with controllable reasoning effort to trade speed for quality. Free until Tuesday June 9. Fast and Pro below 🧵 https://twitter.com/OpenRouter/status/2062951474406240687/photo/1
中文: 在OpenRouter上直播:来自@riverflow_ai的Riverflow 2.5 首个采用独立评分模式的图像模型，可指导其思维和编辑能力，通过可控的推理能力，以速度换取质量。 免费至6月9日星期二。快速与专业 🧵
2026-06-05 17:35:33
OpenRouter
Live on OpenRouter: Riverflow 2.5 from @Sourceful. The first image model with an independent scoring rubric you control to guide its thinking and editing, with controllable reasoning effort to trade speed for quality. Free until Tuesday June 9. Fast and Pro below 🧵 https://twitter.com/OpenRouter/status/2062944965978992935/photo/1
中文: 在OpenRouter上直播:来自@Sourceful的Riverflow 2.5。 首个采用独立评分模式的图像模型，可指导其思维和编辑能力，通过可控的推理能力，以速度换取质量。 免费至6月9日星期二。快速与专业 🧵
2026-06-05 17:09:42
OpenRouter
RT @devfun: we've partnered with @OpenRouter for Poker Arena. they’re giving out free credits for every registered builder. check your em…
中文: RT @devfun:我们已与@OpenRouter合作，为扑克竞技场提供合作关系。 他们为每位注册建筑商提供免费积分。 检查一下你的......
2026-06-04 18:13:13
OpenRouter
DeepSeek has now topped our token share rankings 4 weeks in a row: https://openrouter.ai/rankings https://twitter.com/OpenRouter/status/2062538625225548118/photo/1
中文: DeepSeek 已连续四周位居我们代币分享排行榜榜首:
2026-06-04 14:15:03
OpenRouter
RT @mikeyyyzhao: @OpenRouter + evals has made it easy to experiment and switch between different models. Not trying open source models coul…
中文: RT @mikeyyzhao:@OpenRouter + evals 使得在不同型号之间进行实验和切换变得轻松。不尝试开源模型，这很难......
2026-06-04 14:04:13
OpenRouter
RT @alexatallah: The Big Crunch is here. Companies are realizing: - their inference bill grew 10x in the last few months - another 10x gro…
中文: RT @alexatallah:大关键来了。 企业正在意识到: - 他们的推理账单在过去几个月里增长了10倍 - 又一个10倍......
2026-06-03 14:47:20
OpenRouter
The Pareto Router is now processing almost 1B tokens per day: https://openrouter.ai/openrouter/pareto-code The Auto Router is processing 12B: https://openrouter.ai/openrouter/auto See the @theinformation's article below 👇
中文: 帕雷托路由器目前每天处理近1亿个代币: 自动路由器正在处理12B: 请参阅下方的 @theinformation 文章 👇
2026-06-03 14:34:05
OpenRouter
RT @OpenRouter: Introducing Pareto Code: a new, free, experimental coding router Set `min_coding_score` in your request and route to the c…
中文: RT @OpenRouter:介绍帕雷托代码:一款全新的、免费的实验性编码路由器 在请求中设置 `min_coding_score` 并路由到 c...
2026-06-03 13:47:20
OpenRouter
RT @MicrosoftAI: Making MAI models available on @OpenRouter is about giving builders more flexibility in how they integrate and experiment.
中文: RT @MicrosoftAI:在 @OpenRouter 上提供 MAI 模型，旨在让构建者在集成和实验方面更具灵活性。
2026-06-03 02:27:59
OpenRouter
Three new @MicrosoftAI models now live on OpenRouter! Launching together: MAI-Image-2.5, MAI-Transcribe-1.5, and MAI-Voice-2. More on each below 🧵 https://twitter.com/OpenRouter/status/2061894672847671724/photo/1
中文: 三个新的 @MicrosoftAI 模型现已在 OpenRouter 上上线! 共同发布:MAI-Image-2.5、MAI-Transcribe-1.5 和 MAI-Voice-2。下文各有更多内容 🧵
2026-06-02 19:36:12
OpenRouter
RT @digitalocean: We’re thrilled to be a model provider on @OpenRouter. 🤝🎉 Get access to high-performance inference across open-weight mo…
中文: RT @digitalocean:我们很高兴能成为 @OpenRouter 的模特供应商。🤝🎉 跨开放式重量...获取高性能推理
2026-06-02 17:20:12
OpenRouter
⚡ New provider drop: AI-Native Cloud from @digitalocean is now live on OpenRouter. High performance inference across popular open-weight models. #1 on output speed and latency for DeepSeek V3.2 by @ArtificialAnlys. See their stats and try the models: https://openrouter.ai/provider/digitalocean https://twitter.com/OpenRouter/status/2061840338973806961/photo/1
中文: ⚡ 新服务提供商:来自 @digitalocean 的 AI-Native Cloud 现已在 OpenRouter 上上线。 在流行的开放式重量模型中实现高性能推断。@ArtificialAnlys 在 DeepSeek V3.2 的输出速度和延迟方面排名第一。 查看他们的数据并试用这些模型:
2026-06-02 16:00:18
OpenRouter
RT @jjacky: what's something you built using openrouter this week? share em below 👇🏻 most creative project gets $100 in credits!! (gon…
中文: RT @jjacky:本周你使用 openrouter 构建了什么? 在以下分享 👇🏻 大多数创意项目获得100美元的学分!! (将
2026-06-02 15:20:23
OpenRouter
Rankings of image output models: https://openrouter.ai/rankings#image-output Significant growth in GPT Image 2 last week: https://twitter.com/OpenRouter/status/2061800549083705786/photo/1
中文: 图像输出模型排名: 上周GPT Image 2的显著增长:
2026-06-02 13:22:11
OpenRouter
The Auto Router now lets you tune how it weighs cost against quality. New `cost_quality_tradeoff` parameter, 0 to 10: Set it to 0 and it always picks the most capable model regardless of price. Set it to 10 and the cheapest model wins. https://twitter.com/OpenRouter/status/2061476882470580329/photo/1
中文: 自动路由器现在可让您调整其成本与质量的权衡。 新的 `cost_quality_tradeoff` 参数，0 到 10: 将其设置为0，无论价格如何，它始终选择最有功能的型号。将其设置为10，最低型号获胜。
2026-06-01 15:56:03
OpenRouter
RT @OpenRouter: Guardrails on OpenRouter are the most powerful in the market: centralized security & governance for your AI traffic Budget…
中文: RT @OpenRouter:OpenRouter 上的护栏是市场上最强大的:集中式安全与安普;适用于人工智能流量的治理 预算......
2026-06-01 15:52:39
OpenRouter
Video tutorial: how to build an agent capped at $1000/week with a model denylist & custom data retention Uses the new, stackable Guardrail architecture: https://twitter.com/OpenRouter/status/2061452942385783050/video/1
中文: 视频教程:如何使用模型拒绝列表和示例构建一个每周1000美元的代理;自定义数据留存 使用新型可堆叠的护栏架构:
2026-06-01 14:20:56
OpenRouter
MiniMax-M3 is live on OpenRouter! A frontier-class open-weight model that combines a 1M-token context window, frontier coding and agentic performance, and native multimodality (image & video) in one model. https://twitter.com/OpenRouter/status/2061277148502192246/photo/1
中文: MiniMax-M3 在 OpenRouter 上上线! 一款前沿型开放量型，结合了1M-令牌上下文窗口、前沿编码和代理性能，以及一个模型中的原生多模态(图像和视频)。
2026-06-01 02:42:23
OpenRouter
RT @scaling01: MiniMax-M3 is on OpenRouter - 1 million context - multi-modal - $0.6 / $2.4 per million tokens (input/output) currently…
中文: RT @scaling01:MiniMax-M3 正在 OpenRouter 上 - 100万个背景 - 多模态 - 每百万枚代币(输入/输出)0.6美元/2.4美元，目前...
2026-06-01 01:41:44
OpenRouter
RT @shashankgoyal95: What do you want @OpenRouter to build next?
中文: RT @shashankgoyal95:你接下来希望@OpenRouter 建立什么?
2026-05-31 16:25:54
OpenRouter
RT @DBirker78883: I’m now way more token efficient than before thanks to @OpenRouter and @NousResearch. Using the Hermes 4 70B has been so…
中文: RT @DBirker78883:由于@OpenRouter 和 @NousResearch，我现在比之前更高效了。使用爱马仕4 70B就是如此......
2026-05-31 16:24:19
OpenRouter
RT @shashankgoyal95: #1 on hackernews! So humbled by all the love! So much more coming soon! https://twitter.com/shashankgoyal95/status/2060805047588397263/photo/1
中文: RT @shashankgoyal95:黑客新闻排名第一! 被所有的爱所感动!很快会有更多!
2026-05-30 23:34:53
OpenRouter
RT @KenTheRogers: With all the horror stories of runaway AI spending, this might be worth a look 👀
中文: RT @KenTheRogers:由于人工智能支出失控，这些恐怖故事可能值得一看
2026-05-30 22:30:07
OpenRouter
Guardrails 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! 🧵 https://twitter.com/OpenRouter/status/2060759826708222180/photo/1
中文: OpenRouter 的防护栏是市场上最强大的:集中式安全与安普;为您的人工智能流量提供治理 预算限制、ZDR、模型和放大器;提供者限制、快速注射防御以及DLP/敏感信息检测，分层到您控制的规则中!🧵
2026-05-30 16:26:44
OpenRouter
Now you can use your OpenRouter models directly inside @ComfyUI workflows!
中文: 现在，您可以直接在 @ComfyUI 工作流中使用您的 OpenRouter 模型!
2026-05-29 23:58:32
OpenRouter
OpenRouter now supports "apply_patch," a server tool that lets any model propose file edits using V4A diffs through the Responses API. The model generates a patch (create, update, or delete a file). OpenRouter validates the diff syntax server-side. https://twitter.com/OpenRouter/status/2060395056196936054/photo/1
中文: OpenRouter 现在支持“apply_patch”，这是一种服务器工具，允许任何模型通过响应 API 使用 V4A diffs 提出文件编辑。 模型会生成一个补丁(创建、更新或删除文件)。OpenRouter 验证了 diff 语法服务器端。
2026-05-29 16:17:16
OpenRouter
Step 3.7 Flash from @StepFun_ai is live on OpenRouter. A multimodal (image/video/text) MoE that activates just 11B of 196B params. Tuned for coding, agentic workflows, and structured outputs, with selectable reasoning levels to trade off speed, cost, and depth. https://twitter.com/OpenRouter/status/2060195211113111914/photo/1
中文: @StepFun_ai 的 Step 3.7 Flash 已在 OpenRouter 上实时上线。 一种多模态(图像/视频/文本)，仅激活196B参数中的11B。针对编码、代理工作流程和结构化输出进行调优，并采用可选择的推理等级，以权衡速度、成本和深度。
2026-05-29 03:03:09
OpenRouter
Don't rely on benchmarks; look at the full picture! Try our new Compare page, which also lets you visualize model performance: https://openrouter.ai/compare/openai/gpt-5.5/anthropic/claude-opus-4.7/anthropic/claude-opus-4.8 https://twitter.com/OpenRouter/status/2060142412408717518/video/1
中文: 不要依赖基准，请查看完整图景! 尝试我们的新对比页面，它还可让你可视化模型性能:
2026-05-28 23:33:21
OpenRouter
Opus 4.8 is live on OpenRouter! Same price as 4.7 with gains across agentic coding, reasoning, and computer use. Around 4x less likely than 4.7 to let code flaws pass unremarked. Opus 4.8 Fast Mode is also live - now only 2x the cost for 2.5x the speed. https://twitter.com/OpenRouter/status/2060045716706427212/photo/1
中文: Opus 4.8 在 OpenRouter 上直播! 价格与4.7相同，在代理编码、推理和计算机使用方面都有收益。让代码缺陷无人标识的可能性比4.7小约4倍。 Opus 4.8 快速模式也是实时的，现在仅为 2.5 倍的成本。
2026-05-28 17:09:07
OpenRouter
TIP: You can use Flex and Priority tiers for supported models (OpenAI, Google Vertex, & more) Pricing available on each model page. Docs: https://openrouter.ai/docs/guides/features/service-tiers https://twitter.com/OpenRouter/status/2060007875590697088/photo/1
中文: 提示:您可以使用 Flex 和 Priority 等级来支持的模型(OpenAI、Google Vertex、&更多) 每个型号页面上都有定价。文档:
2026-05-28 14:38:45
OpenRouter
RT @cnorth_13: If you’re burning a lot of money on Claude API tokens, use OpenRouter Fusion to find cheaper models to accomplish the same g…
中文: RT @cnorth_13:如果你在Claude API代币上大量赚钱，请使用OpenRouter Fusion寻找更便宜的模型，以实现相同的目标。
2026-05-28 14:34:27
OpenRouter
RT @luckeyfaraday: Kimi K2.6 is free on @OpenRouter This is the best model for design after Opus 4.7 Take advantage of this https://t.co…
中文: RT @luckeyfaraday:在 @OpenRouter 上，Kimi K2.6 是免费的 这是Opus 4.7之后最适合的设计型号 请使用此
2026-05-28 14:33:42
OpenRouter
RT @code_star: I’ve become a huge fan of @OpenRouter very quickly. It really wouldn’t be possible to even consider testing or talking to a…
中文: RT @code_star:我很快就成了 @OpenRouter 的忠实粉丝。 甚至无法考虑测试或与......交谈
2026-05-27 19:34:17
OpenRouter
Honored to be included in @Redpoint’s 2026 InfraRed 100! https://www.redpoint.com/infrared/report/ https://twitter.com/OpenRouter/status/2059673766989328734/photo/1
中文: 很荣幸能加入@Redpoint的2026年InfraRed 100!
2026-05-27 16:31:07
OpenRouter
RT @alexatallah: A common example of the cost savings people realize when they switch to @OpenRouter https://twitter.com/alexatallah/status/2059664901316972590/photo/1
中文: RT @alexatallah:当人们切换到@OpenRouter时，人们就会意识到节省成本的一个常见例子:
2026-05-27 15:56:18
OpenRouter
RT @warpdotdev: You can now connect your @OpenRouter URL directly to the Warp Agent. OpenRouter unlocks a world of models including Anthro…
中文: RT @warpdotdev:您现在可以将 @OpenRouter 的网址直接连接到 Warp Agent。 OpenRouter 解锁了包括 Anthro 在内的一系列模特世界
2026-05-26 23:22:18
OpenRouter
RT @RonShepherd: Grateful to @m_delamerced and @nytimes for the great write up on @OpenRouter, our recent funding and the shift to multi-mo…
中文: RT @RonShepherd:感谢@m_delamerced和@nytimes，感谢@OpenRouter的精彩文章、我们最近的资金投资以及向多月资金的转型......
2026-05-26 19:03:45
OpenRouter
Today we’re announcing our $113M Series B led by @CapitalGVC. Over the last 6 months, weekly volume on OpenRouter grew from 5T to 25T tokens as AI rapidly shifts from experimentation into production. We’re excited for what comes next. https://twitter.com/OpenRouter/status/2059277623629664758/photo/1
中文: 今天我们宣布由@CapitalGVC领衔的1.13亿美元B轮融资。 在过去6个月里，随着人工智能从实验迅速转向生产，OpenRouter的每周交易量从5T增长到25T。 我们对接下来会发生什么感到兴奋。
2026-05-26 14:16:59
OpenRouter
RT @SimiStern: last year I started building an "AI Council" app of different models but decided it was not worth the effort. This evening…
中文: RT @SimiStern:去年我开始构建一款不同型号的“AI Council”应用程序，但认为这不值得付出。 今天晚上......
2026-05-25 03:22:50
OpenRouter
RT @clark__labs: We now allow you to bring your @OpenRouter key into Clark - our state of the art digital labor agent. By bringing your k…
中文: RT @clark__labs:现在，我们允许您将 @OpenRouter 密钥带入我们最先进的数字劳工代理公司 Clark。 带上你的k...
2026-05-23 19:32:55
OpenRouter
OpenRouter is now supported in @warpdotdev! ❤️
中文: OpenRouter 现已在 @warpdotdev 中支持!❤️
2026-05-22 17:25:31
OpenRouter
DeepSeek V4 Flash has topped the weekly leaderboard https://twitter.com/OpenRouter/status/2057703179882749985/photo/1
中文: DeepSeek V4 Flash 已登上本周排行榜榜首
2026-05-22 06:00:43
OpenRouter
The new Qwen3.7-Max from @Alibaba_Qwen is live on OpenRouter. The flagship of the Qwen3.7 series, built for agent-centric work: coding, office and productivity tasks, and long-horizon autonomous execution. Big jumps in coding and agent benchmarks over Qwen3.6, with explicit… https://twitter.com/OpenRouter/status/2057500097206976983/photo/1
中文: 来自@Alibaba_Qwen的新款Qwen3.7-Max在OpenRouter上直播。 Qwen3.7系列的旗舰产品，以代理为中心的工作:编程、办公和生产力任务，以及长距离的自主执行。在Qwen3.6上，编程和代理基准测试大幅提升，并明确...
2026-05-21 16:33:44
OpenRouter
TIP 💡 You don't have to worry about cache misses for the Auto Router (in addition to all individual models) OpenRouter will keep your session pinned to one model/provider until your cache expires https://twitter.com/OpenRouter/status/2057128446300737702/photo/1
中文: 提示 💡 除了所有独立型号外，您无需担心自动路由器的缓存漏卡问题 OpenRouter 会将您的会话固定在一个模型/提供器上，直到缓存过期
2026-05-20 15:56:55
OpenRouter
RT @gmi_cloud: 05.19.2026 GMI Cloud hits ~90B tokens of DeepSeek V4 in one day on @OpenRouter , ~290B in one week. Thank you to everyone…
中文: RT @gmi_cloud: 05.19.2026 一天内，GMI Cloud 在 @OpenRouter 上达到约 90B 的 DeepSeek V4 代币，一周内达到约290B。 感谢大家......
2026-05-20 01:20:04
OpenRouter
Gemini 3.5 Flash from @GoogleDeepMind is live on OpenRouter! Beats Gemini 3.1 Pro on coding, agentic work, and tool use at Flash-tier price and speed. 1M context, 65K max output, multimodal. $1.50/M input, $9/M output. https://twitter.com/OpenRouter/status/2056805626664431701/photo/1
中文: 来自@GoogleDeepMind的Gemini 3.5 Flash在OpenRouter上直播! 以Flash级价格和速度与Gemini 3.1 Pro进行编程、特工工作和工具使用。 1M 上下文，最大输出 65K，多模态。1.5美元/米输入，9美元/米输出。
2026-05-19 18:34:09
OpenRouter
RT @p0: Parallel Search is now in @OpenRouter. Use Parallel for configurable context size, domain filtering, and clean, structured result…
中文: RT @p0:并行搜索现已在 @OpenRouter 中。 使用 Parallel 进行可配置的上下文大小、域过滤以及简洁、结构化的结果......
2026-05-19 17:49:49
OpenRouter
Any tool-calling model on OpenRouter can call web search and web fetch agentically. The model decides when to search, what to search for, and how many times. We've added @p0 as a new web search provider. Learn more: https://openrouter.ai/announcements/agentic-web-tools https://twitter.com/OpenRouter/status/2056758698400452705/photo/1
中文: OpenRouter 上的任何工具调用模型都可以以特化方式调用网页搜索和网页取款。 模型决定何时搜索、搜索什么以及搜索次数。 我们新增了 @p0 一个新的网页搜索服务提供商。了解更多:
2026-05-19 15:27:41
OpenRouter
3 new models from @xai's Grok creative stack are live on OpenRouter: • Grok Imagine Image Quality: photoreal image generation and editing • Grok Imagine Video: short clips from text, image, or reference • Grok Voice TTS 1.0: 5 voices across 20+ languages More on each below… https://twitter.com/OpenRouter/status/2056448867982606754/photo/1
中文: 来自@xai的Grok创意栈的3款新型号正在OpenRouter上直播: • Grok Imagine 图像质量:真实图像生成与编辑 • Grok Imagine 视频:文字、图片或参考文献的短视频 • Grok 语音 TTS 1.0:20 多种语言的 5 个语音 下文各有更多内容......
2026-05-18 18:56:31
OpenRouter
RT @brexHQ: BREX DATA: Spring 2026’s top 25 fastest-growing software vendors. https://twitter.com/brexHQ/status/2056404447270482056/photo/1
中文: RT @brexHQ:BREX 数据:2026年春季发展最快的25家软件供应商。
2026-05-18 17:37:19
OpenRouter
Some primitives for building long-horizon agents: https://openrouter.ai/long-horizon https://twitter.com/OpenRouter/status/2056404687461519479/photo/1
中文: 构建长水平代理的一些原子:
2026-05-18 16:00:58
OpenRouter
New: an easier-to-use playground sidebar that adapts to the type of model you're trying See @Kling_ai Video v3 in action: https://twitter.com/OpenRouter/status/2056379251562033261/video/1
中文: 全新:一款更易于使用的游乐场侧边栏，可根据您尝试的型号类型进行调整 请参见 @Kling_ai 视频 v3 操作:
2026-05-18 14:19:53
OpenRouter
RT @alexatallah: "But only frontier models are being used!" No, it's a Cambrian explosion of models https://twitter.com/alexatallah/status/2055696592104001578/photo/1
中文: RT @alexatallah:“但只使用前沿模式! 不，这是坎布里亚模式的爆炸式增长
2026-05-16 17:08:01
OpenRouter
RT @benhylak: we ship fast. just published an @OpenRouter agent integration with raindrop. docs below.
中文: RT @benhylak:我们发货很快。刚刚发布了 @OpenRouter 与雨滴的集成。 下图文档。
2026-05-15 22:55:51
OpenRouter
Three big upgrades to BYOK on OpenRouter 🔑 1/ Add multiple keys for the same provider in one workspace and set the order they're tried in. Useful for rotating across rate limits, separating dev and prod credentials, or distributing usage across team accounts! https://twitter.com/OpenRouter/status/2055305259287801865/photo/1
中文: 在 OpenRouter 上对 BYOK 进行三次重大升级 🔑 1 在一个工作区中为同一提供商添加多个密钥，并设置他们已尝试的订单。 适用于跨费率范围旋转、分离开发凭证和 prod 凭据，或在团队账户中分发使用情况!
2026-05-15 15:12:14
OpenRouter
Live on OpenRouter: @recraftai V4.1! Six new image generation models: V4.1 and V4.1 Pro for high aesthetics, V4.1 Vector and V4.1 Pro Vector for SVG illustration, and V4.1 Utility and V4.1 Utility Pro for restraint-first product imagery. Photorealism is more natural, gradients… https://twitter.com/OpenRouter/status/2054957185982177504/photo/1
中文: 在OpenRouter上直播:@recraftai V4.1! 六款新图像生成型号:V4.1 和 V4.1 Pro，用于高美观，V4.1 矢量和 V4.1 Pro 矢量用于 SVG 插画，以及 V4.1 实用工具和 V4.1 实用工具 Pro，用于以约束为先的产品图像。 光现实更自然，有渐变......
2026-05-14 16:09:07
OpenRouter
RT @jjackyliang: i had a BURNING question about ai models as an ex-pubg/apex comp player what if you threw them into a battle royale game,…
中文: RT @jjackyliang:我曾提出过关于作为前pubg/apex comp玩家的AI模特的令人振奋的问题 如果你把他们扔进一场战斗的皇家游戏中会怎么样......
2026-05-14 15:49:15
OpenRouter
RT @joinpursuit: To land a job in the age of AI, make a human connection. Build in public. Be persistent. Our AI-Native Builders sat down…
中文: RT @joinpursuits:要在人工智能时代找到一份工作，请建立人为联系。在公共场合建造。保持毅力。 我们的人工智能原住民建设者坐下来......
2026-05-13 15:32:11
OpenRouter
Opus 4.7 fast mode is live on OpenRouter! Just set your model to `anthropic/claude-opus-4.7-fast` Full Opus 4.7 intelligence with ~2.5x faster throughput https://twitter.com/OpenRouter/status/2054385734665314754/photo/1
中文: Opus 4.7 快速模式在 OpenRouter 上实时显示! 只需将模型设置为“anthropic/claude-opus-4.7-fast” 全Opus 4.7 智能，实现 ~2.5 倍的快速输出
2026-05-13 02:18:22
OpenRouter
Perceptron Mk1 is live on OpenRouter, built by @perceptroninc. Frontier video and embodied reasoning in a vision-language model. Analyzes video at a dynamic frame rate (up to 2 FPS) across a 32k multimodal context, with hybrid reasoning and structured spatial primitives (points,… https://twitter.com/OpenRouter/status/2054232344148787462/photo/1
中文: Perceptron Mk1 在 @perceptroninc 公司的 OpenRouter 上进行直播。 前沿视频，以及视觉语言模型中的具体推理。在32K多模态环境中以动态帧率(高达2帧/小时)分析视频，并采用混合推理和结构空间原语(点，
2026-05-12 16:08:51
OpenRouter
We’re thankful to have been a partner for Anthropic’s Claude Platform on AWS release! It’s seen production OpenRouter traffic, performed consistently, and is now labeled accordingly across all applicable Claude models. https://twitter.com/OpenRouter/status/2054025547962040605/photo/1
中文: 我们非常感谢Anthropic在AWS平台上发布Claude平台的合作伙伴! 已看到生产版OpenRouter的流量，表现稳定，现在在所有适用的Claude型号上都进行了相应标注。
2026-05-12 02:27:07
OpenRouter
Pareto Code is a new way of looking at the Pareto frontier using real market demand DeepSeek V4 Pro is taking the top position, followed by GPT 5.4 Mini and Gemini 3.1 Pro https://openrouter.ai/openrouter/pareto-code https://twitter.com/OpenRouter/status/2053843701261025290/photo/1
中文: 帕雷托码是一种利用实际市场需求看待帕雷托前沿的新方式 DeepSeek V4 Pro 占据首位，随后是 GPT 5.4 Mini 和 Gemini 3.1 Pro
2026-05-11 14:24:31
OpenRouter
RT @WesRoth: OpenRouter has launched "Pareto Code" (openrouter/pareto-code), a free, experimental routing endpoint that automatically sends…
中文: RT @WesRoth:OpenRouter 已推出“Pareto Code”(openrouter/pareto-code)，这是一个免费的实验性路由终端，可自动发送......
2026-05-11 14:15:35
OpenRouter
In case you missed it: Ring-2.6-1T from @AntLingAGI is live and free on OpenRouter through May 15th! A 1T-param thinking model with adjustable thinking effort, capable of tackling your production agent needs.
中文: 如果错过了:@AntLingAGI 的 Ring-2.6-1T 可在 OpenRouter 上直播并免费使用，时间为 5 月 15 日! 一款1T参数思维模型，具有可调节的思维能力，能够满足您的生产代理需求。
2026-05-11 13:46:19
OpenRouter
Even without any subsidies, Anthropic has hit #1 in the tokenshare leaderboard https://twitter.com/OpenRouter/status/2053548965220475115/photo/1
中文: 即使没有任何补贴，Anthropic在代币分享排行榜上也排名第一:
2026-05-10 18:53:21
OpenRouter
Docs from @NousResearch on how to set up Pareto Code in Hermes: https://hermes-agent.nousresearch.com/docs/user-guide/configuration#openrouter-routing--pareto-code-for-auxiliary-tasks https://twitter.com/OpenRouter/status/2053544645410324774/photo/1
中文: 来自@NousResearch的关于如何在爱马仕中设置帕雷托代码的文档:
2026-05-10 18:36:11
OpenRouter
Try out Fusion if you want to get closer to the actual frontier: https://openrouter.ai/labs/fusion https://twitter.com/OpenRouter/status/2053544160985076084/photo/1
中文: 如果想靠近实际前沿，请试试Fusion:
2026-05-10 18:34:15
OpenRouter
RT @ArtificialAnlys: Exciting launch by OpenRouter that uses Artificial Analysis benchmarks
中文: RT @ArtificialAnlys:由OpenRouter推出，采用人工分析基准
2026-05-10 17:53:19
OpenRouter
Introducing Pareto Code: a new, free, experimental coding router Set `min_coding_score` in your request and route to the cheapest code-capable model that clears your bar, ranked by @ArtificialAnlys. See the Pareto frontier shifting in real time👇 https://twitter.com/OpenRouter/status/2053170520087024109/photo/1
中文: 介绍帕雷托代码:一款全新的、免费的实验性编码路由器 在请求中设置 `min_coding_score`，并找到最便宜的可代码编码模型，该模型可清除您的条码，由 @ArtificialAnlys 排名。 实时查看帕雷托边界的变化👇
2026-05-09 17:49:32
OpenRouter
Congrats to @NousResearch!
中文: 恭喜@NousResearch!
2026-05-09 04:19:48
OpenRouter
Jacky starting strong on his first week 👀
中文: 杰基在第一周就开始强势起场👀
2026-05-09 03:02:38
OpenRouter
New in the OpenRouter Agent SDK: human-in-the-loop tools. Auto-resolve routine tool calls. Pause high-stakes ones for review. Return a value to keep the agent running. Return null to surface the call to your app for human input. https://twitter.com/OpenRouter/status/2052856129961758917/photo/1
中文: OpenRouter 代理 SDK 中新增工具:人机工具。 自动解决常规工具调用。暂停高风险审查。 返回一个值以保持代理运行。返回 null 以显示对您应用的人为输入的调用。
2026-05-08 21:00:16
OpenRouter
Live on OpenRouter: @recraftai. Recraft V4 is an image generation model tuned for high aesthetics - art-directed composition, lighting, and color that feels intentional, not stock. Built with artists and designers for branding, conceptual work, and creative exploration. More on… https://twitter.com/OpenRouter/status/2052521915458453894/photo/1
中文: 在OpenRouter上直播:@recraftai。 Recraft V4 是一款专为高美学设计的影像生成模型——以艺术为导向的构图、灯光和色彩，让人感到有意，而不是显得有分量。由艺术家和设计师共同打造，用于品牌推广、概念创作和创造性探索。 更多关于......
2026-05-07 22:52:13
OpenRouter
RT @jjackyliang: 🔫 what does claude opus do when told it needs to be the last surviving? building an agent battle royale w @OpenRouter - m…
中文: RT @jjackyliang:🔫 当被告知该成为最后一个幸存者时，云骋会怎么做? 与@OpenRouter 建立一场代理人战斗——
2026-05-07 21:56:51
OpenRouter
RT @yungalgorithm: damn so much crazy stuff happened today in speech: - @OpenAI releases realtime-2 speech-to-speech - @ElevenLabs reduces…
中文: RT @yungalgoritsm:今天在演讲中发生了太多疯狂的事情: - @OpenAI 发布实时语音转语音 - @ElevenLabs 减少...
2026-05-07 18:54:28
OpenRouter
Gemini 3.1 Flash Lite from @GoogleDeepMind is now GA on OpenRouter. Multimodal (text/image/video/audio/PDF → text), 1M context, selectable thinking levels, at $0.25/M in / $1.50/M out. Also works with our new service_tier param for cost/latency tradeoffs!
中文: 来自@GoogleDeepMind的Gemini 3.1 Flash Lite现已在OpenRouter上推出GA。 多模态(文本/图像/视频/音频/PDF → 文本)，1M 上下文，可选择的思维水平，每米 0.25 美元/美元/美元/美元。 还可与我们的新服务级参数配合使用，以获取成本/延迟的权衡!
2026-05-07 17:43:07
OpenRouter
1/ Audio is now first-class on OpenRouter. Two new endpoints live today: 📢 /api/v1/audio/speech — text-to-speech (TTS) 🎤 /api/v1/audio/transcriptions — speech-to-text (SST) Same routing, billing, and keys you already use for text, image, and video. https://twitter.com/OpenRouter/status/2052396767652544552/photo/1
中文: 现在，Audio 在 OpenRouter 上已成为一流的。 两个新的终点今天就已上线: 📢 /api/v1/audio/speech — 文本转语音(TTS) 🎤 /api/v1/audio/transscriptions — 语音转文本(SST) 已用于文本、图像和视频的路由、计费和密钥。
2026-05-07 14:34:55
OpenRouter
RT @TeksEdge: Have you seen how many free models are available on @OpenRouter? It’s at least 30 by my recent count. There’s even an API tha…
中文: RT @TeksEdge:您看到 @OpenRouter 上有多少个免费型号吗?根据我最近的统计，至少已经30了。甚至还有一个API......
2026-05-05 14:12:33
OpenRouter
We analyzed GPT 5.5 vs GPT 5.4 and found that costs increased between 49-92%. The 2x price hike of GPT 5.5 is mitigated by the model generating 19-34% fewer completion tokens for longer prompts. More analysis here: https://openrouter.ai/announcements/gpt55-cost-analysis https://twitter.com/OpenRouter/status/2051500175554654467/photo/1
中文: 我们分析了GPT 5.5与GPT 5.4的对比，发现成本在49-92%之间有所上升。 GPT 5.5 的 2 次价格上涨因该模型导致完成代币减少 19 至 34%，持续时间更长而有所缓解。 更多分析请点击此处:
2026-05-05 03:12:11
OpenRouter
RT @luckeyfaraday: I did it I generated 100M tokens on @OpenRouter for free All thanks to Owl-Alpha For reference Opus 4.7 costs 5$/M in…
中文: RT @luckeyfarady:我做到了 我免费在@OpenRouter上生成了100万枚代币 感谢Owl-Alpha 供参考:Opus 4.7 费用 5$/M 在...
2026-05-04 16:00:22
OpenRouter
Own your data. One-click ZDR: https://openrouter.ai/workspaces/default/guardrails/default/models https://twitter.com/OpenRouter/status/2051289713319858313/photo/1
中文: 拥有您的数据。一键ZDR:
2026-05-04 13:15:53
OpenRouter
RT @alexatallah: OpenRouter can now cache your LLM responses for free!
中文: RT @alexatallah:OpenRouter 现在可以免费缓存您的 LLM 回复!
2026-05-04 13:11:29
OpenRouter
RT @alexatallah: More about OpenRouter Enterprise: https://openrouter.ai/enterprise It's best way to use LLMs at scale, and we're making it better…
中文: RT @alexatallah:关于OpenRouter Enterprise的更多信息: 大规模使用LLM是最好的方法，而且我们正在让它变得更好......
2026-05-02 20:19:25
OpenRouter
Introducing Response Caching: save tons of money and time on tests and agent retries. Blog post: https://openrouter.ai/announcements/response-caching Available for free. Learn more 👇 https://twitter.com/OpenRouter/status/2050616590098473445/photo/1
中文: 介绍响应缓存:在测试和代理重试中节省大量金钱和时间。 博客文章: 免费提供。了解更多 👇
2026-05-02 16:41:08
OpenRouter
RT @r_marked: S/o @OpenRouter for building the best AI routing solution on the market. If you are working with LLM APIs, you should be usin…
中文: RT @r_marked:用于构建市场上最佳人工智能路由解决方案的 @OpenRouter。如果你正在使用 LLM API，你应该使用......
2026-05-02 16:18:18
OpenRouter
NEW: "-latest" model aliases 🔀 Route requests to "~anthropic/claude-opus-latest", "~openai/gpt-latest", etc to get the latest version of each major model. (Inspired by semver.) https://openrouter.ai/models?q=latest https://twitter.com/OpenRouter/status/2050610378971738552/photo/1
中文: 最新“最新”型号别名 🔀 向“~anthropic/claude-opus-latest”、“~openai/gpt-latt”等路线请求，以获取每种主要型号的最新版本。(灵感来自 semver。)
2026-05-02 16:16:27
OpenRouter
Notice: there’s a bug in this Azure data that we’re working on correcting, due to a change in their error shapes upstream. But gpt5.5 is seeing a lot of growth!
中文: 请注意:由于我们正在处理的Azure数据存在错误，因为其错误形状在上游发生了变化。 但gpt5.5正在实现大量增长!
2026-05-02 01:39:30
OpenRouter
The new Grok-4.3 from @xai is live on OpenRouter! Grok-4.3 releases at a lower price than Grok-4.2, while seeing a large jump in agentic performance: a 321 point increase to 1500 ELO on @ArtificialAnlys GDPval-AA, surpassing other top models despite the lower price. https://twitter.com/OpenRouter/status/2049996465263759563/photo/1
中文: @xai 的新 Grok-4.3 在 OpenRouter 上直播! Grok-4.3 的发布价格低于 Grok-4.2，而 proetic 性能大幅提升:@ArtificialAnlys GDPval-AA 的 15 点涨幅为 321 点，达到 1500 个 ELO，尽管价格较低，但仍超过了其他顶级车型。
2026-04-30 23:36:59
OpenRouter
alphaXiv x OpenRouter is live! When an AI paper mentions a model, alphaXiv now turns it into a preview: provider, description, use-case rankings, and a direct link to the OpenRouter model page. Go from research to model in one click with @askalphaxiv https://twitter.com/OpenRouter/status/2049866529760755826/photo/1
中文: alphaXiv x OpenRouter 是实时的! 当一篇AI论文提到一个模型时，alphaXiv 现在将其变成一个预览版:提供者、描述、用例排名，以及指向 OpenRouter 模型页面的直接链接。 只需点击一下:@askalphaxiv，即可从研究转到模型
2026-04-30 15:00:40
OpenRouter
New stealth model: Owl Alpha! Owl is a high-performance foundation model designed for agentic workloads. Powerful tool use capabilities and a 1M context window, ready for use in all your favorite productivity apps. Try it now and share feedback to improve the model! https://twitter.com/OpenRouter/status/2049864339570757920/photo/1
中文: 全新隐身型号:Owl Alpha! Owl 是一款专为代理工作负载设计的高性能基础模型。强大的工具使用功能和1M上下文窗口，可随时用于您喜爱的所有生产力应用。 立即尝试，分享反馈以改进模型!
2026-04-30 14:51:57
OpenRouter
RT @jjackyliang: first day at @OpenRouter as dev rel lead 🥳🔥 the future is multi-model!!
中文: RT @jjackyliang:首日 @OpenRouter 担任 dev rel 领先 🥳🔥 未来是多模型!
2026-04-30 14:29:55
OpenRouter
RT @Ace_Builder_: I am averaging $0.012 (ONE CENT) spent per 1M Tokens used with @deepseek_ai V4 Flash using @NousResearch hermes agent due…
中文: RT @Ace_Builder_:我使用@NousResearch 的 research 信息代理，使用 @deepseek_ai V4 Flash 时，平均每 100 万美元(一分)。
2026-04-30 14:12:43
OpenRouter
`stripe projects add openrouter/api` An easy way to accept @stripe payments for 400+ LLMs and image/video/audio models, now available to all! https://openrouter.ai/announcements/openrouter-on-stripe-projects https://twitter.com/OpenRouter/status/2049532448711823697/photo/1
中文: 条纹项目添加 openrouter/api 一种便捷的方式，可轻松接受400多种LLM和图像/视频/音频型号的@stripe付款，现可向所有人开放!
2026-04-29 16:53:08
OpenRouter
https://twitter.com/OpenRouter/status/2049527964707229949/photo/1
2026-04-29 16:35:19
OpenRouter
Kimi K2.6 is the first model to break 2T tokens/week on OpenRouter: https://openrouter.ai/rankings https://twitter.com/OpenRouter/status/2049524788323074374/photo/1
中文: Kimi K2.6 是首个在 OpenRouter 上打破 2T 代币发行/周模式的机型:
2026-04-29 16:22:42
OpenRouter
RT @alexatallah: New American lab focused on coding. Trained completely in-house on 30T tokens "by completing millions of tasks in tens of…
中文: RT @alexatallah:专注于编程的美国新实验室。完全在30T代币上进行内部训练 通过完成数以十计的任务来完成......
2026-04-29 11:01:34
OpenRouter
New public rankings: Audio Input! @GoogleDeepMind's Gemini models take the top 7 (!!) slots this week, with Gemini 3 and 2.5 Flash models processing >50% of prompts. https://twitter.com/OpenRouter/status/2049313996214603902/photo/1
中文: 新公众排名:音频输入! @GoogleDeepMind 的 Gemini 型号位居前列 7 位(!!)本周的时段，Gemini 3 和 2.5 Flash 机型的处理 >50% 提示。
2026-04-29 02:25:05
OpenRouter
Welcome @KenTheRogers to the team! Expect to see some technical guides, cookbooks, and more coming from him. He's the author of our first X article 👇
中文: 欢迎@KenTheRogers加入团队!期待看到一些技术指南、烹饪书以及更多来自他的书籍。他是我们第一篇X文章的作者👇
2026-04-28 17:10:54
OpenRouter
NVIDIA Nemotron™ 3 Nano Omni is live on OpenRouter. An open 30B-A3B multimodal model for agentic workflows: text, image, video, and audio in → text out, with a 256k context window and efficient MoE architecture for computer use, documents, and AV reasoning. https://twitter.com/OpenRouter/status/2049164366218772526/photo/1
中文: NVIDIA Nemotron™ 3 Nano Omni 已在 OpenRouter 上上线。 一款适用于代理工作流程的开放式30B-A3B多模态模型:文本、图像、视频和音频 → 文本退出，具有256k上下文窗口和高效的MoE架构，适用于计算机使用、文档和音频推理。
2026-04-28 16:30:31
OpenRouter
We studied data across the market for Opus 4.7 and found that costs increased 12–27%, with the exception of short prompts, which actually got more cost efficient. Full post: https://openrouter.ai/announcements/opus-47-tokenizer-analysis https://twitter.com/OpenRouter/status/2049154984810578168/photo/1
中文: 我们研究了Opus 4.7市场的数据，发现成本增长了12-27%，但短期提示除外，实际上提高了成本效率。 完整文章:
2026-04-28 15:53:14
OpenRouter
The first public foundation models from @poolsideai just dropped on OpenRouter! Laguna M.1 and Laguna XS.2. Built from scratch for agentic coding and long-horizon work. Free for a limited time ⬇️ https://twitter.com/OpenRouter/status/2049145538373947541/photo/1
中文: @poolsideai 的首批公共基金会模型刚刚在 OpenRouter 上下落! 拉古纳 M.1 和拉古纳 XS.2。专为自编码和长距离工作而从零开始构建。限时免费⬇️
2026-04-28 15:15:42
OpenRouter
RT @AshExplained: I made an openrouter account and I created an mcp to get nano banana and video creation apis, now my claude code has acce…
中文: RT @Ash Explained:我创建了一个开户账户，并创建了一个 mcp 来获取纳米香蕉和视频制作，现在我的云片代码已经成功了......
2026-04-28 14:31:04
OpenRouter
RT @alexatallah: @aparnadhinak Great article! pulled some of these ideas into @OpenRouter's agent harness skills: https://github.com/OpenRouterTeam/skills/pull/36
中文: RT @alexatallah:@aparnadhinak 很棒的文章!将其中一些想法融入到@OpenRouter的代理抓取技能中:
2026-04-28 00:37:06
OpenRouter
RT @karllorey: Looking at you, @OpenRouter 😏 https://twitter.com/karllorey/status/2048893466613076296/photo/1
中文: RT @karllorey:看着你，@OpenRouter 😏
2026-04-27 23:22:33
OpenRouter
RT @tomosman: Went pretty hard on a full build test today. - Hooked in @OpenRouter (GLM 5.1 + Deepseek V4) - Ran it up to a 6-agent team b…
中文: RT @tomosman:今天在全面构建测试上进行了相当艰苦的测试。 - 连接在 @OpenRouter(GLM 5.1 + Deepseek V4)中 - 将其发展到一支由6名经纪人组成的团队。
2026-04-27 22:04:27
OpenRouter
RT @int32max: @OpenRouter kimi model with @badlogicgames pi has brought back so much of that neovim feeling that I was missing engineerin…
中文: RT @int32max:@OpenRouter 的 kimi 模特 @badlogicgames pi 让我重新感受到了那种新的感觉 工程师......
2026-04-27 19:01:55
OpenRouter
RT @sensdlx: Tested @OpenRouter ’s “create headless agent” skill for a narrow Hermes worker. 2 URLs in. Strict JSON + X/Markdown artifacts…
中文: RT @sensdlx:测试了@OpenRouter为一位狭小的爱马仕员工打造的“无头代理”技能。 输入两个网址。 严格的 JSON + X/Markdown 工件...
2026-04-27 04:28:39
OpenRouter
New skill that some of you requested: "create-headless-agent" This skill walks you through building a customizable, multi-model, headless CLI tool using @bunjavascript. Blog post about both skills here: https://openrouter.ai/announcements/create-agent-harness-with-agent-sdk
中文: 你们中有些人所要求的新技能:“无头创造者” 这项技能可引导您使用 @bunjavascript 构建一个可自定义、多模型、无头的 CLI 工具。 关于这两种技能的博客文章请点击此处:
2026-04-26 21:01:02
OpenRouter
RT @morganlinton: Okay, just made the repo for Small Harness public, and Open Source. This is the first official release from @getsmallai ✨…
中文: RT @morganlinton:好的，刚刚公开了《小哈尼特》和《开源》。这是@getsmallai ✨ 发布的首个正式版本。
2026-04-26 15:48:16
OpenRouter
RT @morganlinton: Okay, spent some time this afternoon working on building a harness for small llms, and I have to say, it is totally fasci…
中文: RT @morganlinton:今天下午花了一些时间为小小小花束制作线束，我不得不说，这完全是一成是事实......
2026-04-26 00:52:24
OpenRouter
RT @matvelloso: I don't say this often enough, but @OpenRouter is just awesome. Being able to easily experiment with a bunch of different m…
中文: RT @matvelloso:我经常说这个，但@OpenRouter 真是太棒了。能够轻松地尝试许多不同的......
2026-04-25 05:53:15
OpenRouter
RT @digitalocean: We're bringing the Agentic Inference Cloud to San Francisco with the help of our sponsors. 🤝 @nvidia, @arcee_ai, @vast_ai…
中文: RT @digitalocean:我们将借助赞助商的帮助，将代理推理云引入旧金山。🤝 @nvidia，@arcee_ai，@vast_ai......
2026-04-25 00:34:57
OpenRouter
RT @TeksEdge: Using Kimi K2.6 on @OpenRouter via a US provider, and it has passed my coding benchmark. I can attest this model is for real.
中文: RT @TeksEdge:通过美国服务提供商在 @OpenRouter 上使用 Kimi K2.6，并且已超过我的编码基准。我可以证明这个模型是真实的。
2026-04-25 00:34:44
OpenRouter
RT @alexatallah: 👀 @badlogicgames https://twitter.com/alexatallah/status/2047836033866420401/photo/1
2026-04-25 00:33:59
OpenRouter
RT @gdb: SOTA perf from GPT-5.5 for long-running tasks:
中文: RT @gdb:GPT-5.5 的 SOTA perf 用于长期任务:
2026-04-24 23:53:06
OpenRouter
Congrats to @badlogicgames and the Pi community! Pi jumps into the top 5 CLI agents on OpenRouter within 5 days of setting up app attribution.
中文: 恭喜 @badlogicgames 和 Pi 社区! 在设置应用归因后的5天内，Pi 跳入 OpenRouter 上排名前 5 的 CLI 代理。
2026-04-24 23:45:01
OpenRouter
OpenAI's GPT-5.5 and GPT-5.5 Pro are live now on OpenRouter! GPT-5.5 is SOTA for long running work across code, data, and tools, with GPT-5.5 Pro for more complex reasoning and analysis. https://twitter.com/OpenRouter/status/2047744317415141787/photo/1
中文: OpenAI的GPT-5.5和GPT-5.5 Pro现已上线OpenRouter! GPT-5.5 是用于代码、数据和工具长期运行的 SOTA，支持 GPT-5.5 Pro，用于更复杂的推理和分析。
2026-04-24 18:27:45
OpenRouter
Introducing "create-agent-tui" A skill for building your own agent harness + terminal UI (TUI). The skill walks you through 4 different ways of customizing the look, and supports dozens of optional features 👇 https://twitter.com/OpenRouter/status/2047701992798392484/video/1
中文: 引入“create-agent-tui” 打造自有设备 pleat + 终端 UI(TUI)的技能。该技能可引导您了解自定义外观的4种不同方式，并支持数十种可选功能👇
2026-04-24 15:39:34
OpenRouter
DeepSeek V4 Pro and V4 Flash are live on OpenRouter! @deepseek_ai's latest models show a huge jump in capabilities compared to V3.2, and meet or surpass current SOTA models across a variety of benchmarks. https://twitter.com/OpenRouter/status/2047528986293772792/photo/1
中文: DeepSeek V4 Pro 和 V4 Flash 可在 OpenRouter 上实时使用! @deepseek_ai 的最新型号显示，与 V3.2 相比，其性能大幅提升，在多个基准测试中均达到或超越了当前的 SOTA 型号。
2026-04-24 04:12:06
OpenRouter
https://x.com/i/article/2047496116501880832
2026-04-24 02:41:27
OpenRouter
The new Hy3-Preview model from @TencentHunyuan is live for free on OpenRouter! It’s a 295B MoE model (21B active) with controllable reasoning effort. A cost-effective, practical model that performs strongly in coding agents and delivers comprehensive general capabilities. https://twitter.com/OpenRouter/status/2047356098764808289/photo/1
中文: @TencentHunyuan 的新 Hy3-Preview 型号在 OpenRouter 上免费上线! 这是一个295B的MoE模型(21B正动)，具有可控的推理能力。 一种经济高效、实用的模型，在编码代理中表现强劲，并具备全面的通用功能。
2026-04-23 16:45:06
OpenRouter
Introducing Workspaces! Organize your OpenRouter projects into separate environments, each with its own API keys, routing, guardrails, and observability. https://www.youtube.com/watch?v=ZPQil3VlK9Q
中文: 介绍工作区! 将您的OpenRouter项目组织成各自不同的环境，每个项目都配有独立的API密钥、路由、护栏和可观测性。
2026-04-23 16:31:44
OpenRouter
Stay tuned for an exciting openrouter/agent SDK tutorial, coming tomorrow! Start building on the top floor, on battle-tested abstractions that scale with model intelligence: https://openrouter.ai/sdk
中文: 敬请关注，明天将推出一个精彩的开场/代理SDK教程! 开始在顶层进行建设，采用经过战斗考验的抽象概念，这些抽象作品以模型智能为规模:
2026-04-23 16:15:46
OpenRouter
RT @pierceboggan: Bring your own key in @code is now available to all Copilot plans, including Free, Pro, Pro+, Business, and Enterprise!…
中文: RT @pierceboggan:现在所有 Copilot 套餐(包括 Free、Pro、Pro+、Business 和 Enterprise!)都可在 @code 中自带密钥!......
2026-04-23 01:22:51
OpenRouter
RT @the_zmll: I just got Gemini, Claude Code, and Codex to self-organise with absolutely no orchestrating from my end besides "hold a meeti…
中文: RT @the_zmll:我刚刚让双子座、克劳德·德克斯和法典自我组织，除了“举行会面”之外，我完全无需任何安排。
2026-04-23 01:21:03
OpenRouter
RT @alexatallah: Compare Nano Banana & GPT-Image-2 head-to-head: https://openrouter.ai/compare/google/gemini-3.1-flash-image-preview/openai/gpt-5.4-image-2 https://twitter.com/alexatallah/status/2047104505926606928/photo/1
中文: RT @alexatallah:比较纳米香蕉和大麻;GPT-Image-2 正面交锋:
2026-04-23 00:05:44
OpenRouter
The incredibly powerful new GPT Image 2 model from @OpenAI is live on OpenRouter as openai/gpt-5.4-image-2 Using OpenRouter's GPT-5.4 Image 2, you get the image gen capabilities of Image 2 alongside the prompt improvement of GPT-5.4. https://twitter.com/OpenRouter/status/2047055195474145334/photo/1
中文: @OpenAI 的全新 GPT 图像 2 功能极强，在 OpenRouter 上以 openai/gpt-5.4-image-2 为真人 使用 OpenRouter 的 GPT-5.4 图像 2，您可获取图像生成功能，同时快速提升 GPT-5.4。
2026-04-22 20:49:25
OpenRouter
MiMo-V2.5 series from @XiaomiMiMo is live now on OpenRouter! Both V2.5 and V2.5-Pro see improvements over V2-Pro and V2-Omni, with a focus on long running agent tasks and coding ability. They also both launch with 1 million context, and are extremely token efficient. https://twitter.com/OpenRouter/status/2046990572725182964/photo/1
中文: @XiaomiMiMo 的 MiMo-V2.5 系列现已在 OpenRouter 上线! V2.5 和 V2.5-Pro 均在 V2-Pro 和 V2-Omni 上均实现了改进，专注于长期运行的代理任务和编码能力。它们同时推出，支持100万个上下文，且具有极高的代币效率。
2026-04-22 16:32:38
OpenRouter
RT @KenTheRogers: Been testing out Kimi K2.6 in Hermes by building a nifty little CLI tool using @OpenRouter's Agent SDK. So far really en…
中文: RT @KenTheRogers:通过使用 @OpenRouter's Agent SDK 构建一个漂亮的小 CLI 工具，在 Hermes 中测试 Kimi K2.6。 到目前为止，真的......
2026-04-22 00:44:04
OpenRouter
Stealth model reveal! The Elephant Alpha model is live now as @AntLingAGI's new Ling-2.6-flash. Elephant topped the trending charts on OpenRouter throughout its stealth period and will continue free for one week. https://twitter.com/OpenRouter/status/2046663534583701506/photo/1
中文: 隐秘模型揭晓! 大象阿尔法模型现在以@AntLingAGI的全新Ling-2.6闪存线为生。 大象在OpenRouter的隐身期间位居榜首，将免费持续一周。
2026-04-21 18:53:06
OpenRouter
RT @alexatallah: OpenRouter is, simply, the easiest way to set up sovereign AI and private inference for all models and providers
中文: RT @alexatallah:OpenRouter 是为所有模型和提供商设置主权人工智能和私有推理的最简单方法
2026-04-21 18:12:05
OpenRouter
RT @datadogdevs: Co-founder and CTO of @OpenRouter, @alexatallah, provides insights in @datadoghq's State of AI Engineering report, now out…
中文: RT @datadogdevs:@OpenRouter 的联合创始人兼首席技术官，@alexatallah，提供 @datadoghq 人工智能工程状况报告的见解，现已公布...
2026-04-21 17:54:52
OpenRouter
RT @firecrawl: Firecrawl is now a search provider in @OpenRouter 🔥 Ground any OpenRouter model in full web pages instead of search snippet…
中文: RT @firecrawl:Firecrawl 现已在 @OpenRouter 中提供搜索服务 🔥 将任何OpenRouter模型都用于完整网页，而不是搜索片段......
2026-04-21 17:54:33
OpenRouter
What is Sovereign AI? In short, running AI entirely within a given region, with no cross-border data transfers, no provider data retention, and no training on your data. OpenRouter was the first platform to enable this across providers. More info: https://openrouter.ai/docs/guides/get-started/sovereign-ai https://twitter.com/OpenRouter/status/2046648607231930466/photo/1
中文: 什么是主权人工智能? 简而言之，完全在特定区域内运行人工智能，无需跨境数据传输、无需提供者数据留存，也无需对数据进行培训。 OpenRouter 是首个在各供应商之间实现此内容的平台。更多信息:
2026-04-21 17:53:47
OpenRouter
What is Sovereign AI? In short, running AI entirely within a given region, with no cross-border data transfers, no provider data retention, and no training on your data. OpenRouter was the first platform to enable this across providers. More info: https://openrouter.ai/docs/guides/get-started/sovereign-ai
中文: 什么是主权人工智能? 简而言之，完全在特定区域内运行人工智能，无需跨境数据传输、无需提供者数据留存，也无需对数据进行培训。 OpenRouter 是首个在各供应商之间实现此内容的平台。更多信息:
2026-04-21 17:53:31
OpenRouter
RT @michellechen: kimi k2.6 on @CloudflareDev workers ai, now live on @OpenRouter 🌙 https://twitter.com/michellechen/status/2046302713865175497/photo/1
中文: RT @michellechen: kimi k2.6 关注 @CloudflareDev 员工，现在 @OpenRouter 🌙 上直播
2026-04-20 21:33:46
OpenRouter
Kimi K2.6 is live on OpenRouter! @Kimi_Moonshot's new model is a long-horizon coding model built for sustained agentic work. It behaves more like a systems engineer than a chatbot, with the stamina to decompose, execute, and optimize complex tasks. Try it in all your favorite… https://twitter.com/OpenRouter/status/2046259590774571199/photo/1
中文: Kimi K2.6 在 OpenRouter 上直播! @Kimi_Moonshot 的新模型是一种长寿命编程模型，旨在持续进行特效工作。它的行为更像一个系统工程师，而不是一个聊天机器人，其需要分解、执行和优化复杂任务的耐力。 在你最喜欢的内容中尝试一下......
2026-04-20 16:07:58
OpenRouter
RT @llmDestructor: @OpenRouter agent sdk is very cool trying it out
中文: RT @llmDestructor:@OpenRouter 代理 sdk 试试点点
2026-04-18 16:41:28
OpenRouter
RT @OpenRouter: Video generation is now live on OpenRouter! One API gives you access to the top video models, right alongside your text, i…
中文: RT @OpenRouter:视频生成现已上线，上线至OpenRouter! 一个API可让你直接访问顶部视频模型，与文本并列......
2026-04-17 21:55:17
OpenRouter
RT @patrickc: Just launched some great new providers in Stripe Projects (https://t.co/QwQF6d2TIz): @huggingface @Cloudflare @OpenRouter @f…
中文: RT @patrickc:刚刚在Stripe Projects( @huggingface @Cloudflare @OpenRouter @f...
2026-04-16 20:44:49
OpenRouter
RT @stripe: New providers now available in Stripe Projects: @huggingface @Cloudflare @OpenRouter @firecrawl @flydotio @Amplitude_HQ @mixpan…
中文: RT @stripe:Stripe Projects 现已推出新服务商: @huggingface @Cloudflare @OpenRouter @firecrawl @flydotio @Amplitude_HQ @mixpan...
2026-04-16 19:30:23
OpenRouter
Claude Opus 4.7 is live on OpenRouter! @AnthropicAI's most capable Opus model showed improvements in complex and long running coding tasks in our early testing, where it more consistently checked its own work before claiming a task wask completed. https://twitter.com/OpenRouter/status/2044790677138178349/photo/1
中文: 克劳德·奥普斯 4.7 在 OpenRouter 上直播! @AntropicAI 最强大的 Opus 模型在早期测试中展示了复杂且长期运行的编程任务的改进，在完成任务之前，它更持续地检查了自身的工作。
2026-04-16 14:51:02
OpenRouter
RT @alexatallah: Since launching media-gen models, we've seen over 100m generations and 50% MoM growth. Video on @OpenRouter does a few th…
中文: RT @alexatallah:自推出媒体代代代代相传以来，我们已经看到了超过1亿代和50%的MoM增长。 @OpenRouter 上的视频会制作几个......
2026-04-15 19:41:53
OpenRouter
RT @b3nhuang: Just for fun I made a benchmark of the models trading oil. I ran 9 frontier LLMs trading from 1/1 => 3/14 Oil was up 72% so…
中文: RT @b3nhuang:我为了好玩，就为了换取石油的模型，我做了一个标杆。我从1/1 => 3/14开始运行了9个前沿LLM交易 油价上涨了72%，因此......
2026-04-15 19:39:34
OpenRouter
Video generation is now live on OpenRouter! One API gives you access to the top video models, right alongside your text, images, audio, embeddings, and reranker generations. Watch our human-generated launch video: https://twitter.com/OpenRouter/status/2044472220462801053/video/1
中文: 视频生成现已在 OpenRouter 上上线! 一个API可让您直接访问顶级视频模型，与文字、图像、音频、嵌入以及重新排名的世代并列。观看我们的人类制作发布视频:
2026-04-15 17:45:36
OpenRouter
RT @emmamariecryer: i love dreamers :) so i am giving away $100 in @OpenRouter credits to a bootstrapped founder to help your journey along…
中文: RT @emmariecryer:我热爱梦想家:) 我将捐赠100美元，以@OpenRouter的功劳，帮助一位被引导的创始人，帮助你一路走来......
2026-04-15 15:49:08
OpenRouter
RT @Sandeepg33k: Nice to see the my little project reach ~80 stars! Added some improvements: - @OpenRouter support - Tab Manager, if a u…
中文: RT @Sandeepg33k:很高兴看到我的小项目达到了约80星! 增加了一些改进: - @OpenRouter 支持 - 标签管理器，如果是...
2026-04-15 12:57:44
OpenRouter
New on OpenRouter: Reranker Models 🔍 Why add a reranker to your RAG pipeline? Embedding search finds relevant chunks, but rerankers tell you which ones are MOST relevant and result in significantly better answers. Now live via a single API endpoint, starting with @cohere! https://twitter.com/OpenRouter/status/2044070463723204730/photo/1
中文: OpenRouter 上的新机型:重机模型 🔍 为什么要在你的RAG管道中添加一个重新排名者?嵌入搜索会找到相关的部分，但重新排名的人会告诉你哪些最相关，并能带来更优厚的答案。 现在通过单个API端点进行直播，从@cohere开始!
2026-04-14 15:09:10
OpenRouter
RT @alexatallah: Opus 4.6 is seeing 6-8% higher uptime on OpenRouter, sometimes passing 20% https://twitter.com/alexatallah/status/2044062715396677807/photo/1
中文: RT @alexatallah:Opus 4.6 的 OPus 4.6 在 OpenRouter 上的上涨时间上涨了 80%，有时超过 20% 的
2026-04-14 14:42:09
OpenRouter
RT @Teknium: NEW: Added @OpenRouter's new free stealth model, Elephant-Alpha, to Hermes Agent, which you can now access if you run `hermes…
中文: RT @Teknium:新:将 @OpenRouter 的全新免费隐身模型 Elephant-Alpha 添加到 Hermes Agent 中，如果您运行“hermes”，现在可以访问该模型。
2026-04-14 11:54:20
OpenRouter
🥷 Welcoming a new stealth model on OpenRouter: Elephant Alpha. Elephant is a 100B parameter instant model, matching SOTA performance of similar scale while being extremely token efficient. Strong at code completion, debugging, document processing, and lightweight agents. https://twitter.com/OpenRouter/status/2043714975756390844/photo/1
中文: 🥷 在《OpenRouter: Elephant Alpha》上迎来一款全新的隐身模型。 Elephant 是一个 100B 参数即时模型，与类似比例的 SOTA 性能相匹配，同时具有极高的代币效率。擅长代码完成、调试、文档处理和轻量级代理。
2026-04-13 15:36:35
OpenRouter
RT @jjacky: answer hq agent must be wondering wtf i'm looking for but yayyyyy, a simple agentic loop built on @OpenRouter works! with zen…
中文: RT @jjacky:答题代理人一定在想我要找 但 yayyyyyy，一个基于 @OpenRouter 构建的简单代理循环!禅......
2026-04-13 03:08:37
OpenRouter
RT @alexatallah: Looking for a summer intern who can help me automate more of my work. Benefits: - learn how a high-velocity, remote-first…
中文: RT @alexatallah:正在寻找一位暑期实习生，帮助我实现更多工作自动化。优点: - 了解高速、远程优先的...
2026-04-11 18:23:07
OpenRouter
RT @packlesshepherd: I coded up an open-source, not-for-profit AI paper reviewer that rivals the performance of @reviewer3com, @RefineInk,…
中文: RT @packlesshepherd:我为一位开源的、非营利性的AI纸质评论者编写了代码，它与@reviewer3com、@RefineInk的表现相媲美......
2026-04-11 18:20:47
OpenRouter
RT @packlesshepherd: Update: you can now log in directly with your @OpenRouter account too instead of having to manually drop in your API k…
中文: RT @packlesshepherd:更新:您现在也可以直接使用 @OpenRouter 账户登录，而无需手动登录您的 API k...
2026-04-11 03:12:48
OpenRouter
RT @muhashmii: btw, you can spin up an agent on a @daytonaio sandbox with one command (courtesy of @OpenRouter's spawn cli) 🤩 here's me sp…
中文: RT @muhashmie:你可以用一个命令(由 @OpenRouter 的 spowt cli)在 @daytonaio 沙盒上生成一个代理。🤩 这儿是我......
2026-04-10 19:18:07
OpenRouter
RT @alexatallah: Some upgrades are coming soon to the @OpenRouter Auto Router, to help you pick the lowest-cost model that fits your worklo…
中文: RT @alexatallah:一些升级即将升级到 @OpenRouter 自动路由器，帮助您选择适合工作的最低成本型号。
2026-04-10 19:17:58
OpenRouter
Hitting model limits mid-session is painful See how Ewan Jones rebuilt his setup around @zeddotdev and OpenRouter credits that roll over instead of resetting. Works with Claude Code too. https://braw.dev/blog/2026-04-06-reallocating-100-month-claude-spend/
中文: 中期击球模型限制令人痛苦 看看伊万·琼斯如何围绕@zeddotdev和OpenRouter的积分重建，这些积分会逐渐恢复，而非重置。 也可与Claude Code配合使用。
2026-04-10 15:38:25
OpenRouter
RT @ScottWu46: btw you can see this effect live on OpenRouter: total # tokens has gone from 1.78T / wk one year ago to 27T / wk today (15.…
中文: RT @ScottWu46:现在您可以在 OpenRouter 上实时看到此效果: 总代币总数已从一年前的1.78T/wk，今天从27T/wk(15个)。......
2026-04-09 15:26:26
OpenRouter
Model comparison pages now show benchmarks. Click "Compare" at the top of any model page to get started https://twitter.com/OpenRouter/status/2042253685296599404/photo/1
中文: 模型对比页现在显示基准。 单击任何模型页面顶部的“比较”按钮，即可开始
2026-04-09 14:49:56
OpenRouter
How to enable /fast mode within Claude Code: https://openrouter.ai/docs/guides/coding-agents/claude-code-integration#fast-mode https://twitter.com/OpenRouter/status/2042246609824596055/photo/1
中文: 如何在克劳德代码中启用/快速模式:
2026-04-09 14:21:49
OpenRouter
RT @drose101: ok i just did a full migration to @OpenRouter its so much easier to just use a single source for all my modeling calls. looks…
中文: RT @drose101:好吧，我刚刚完全迁移到 @OpenRouter，几乎更方便地使用单个源来查看我所有的建模通话。
2026-04-08 19:44:50
OpenRouter
Qwen3.6-Plus free trial has ended, and is now live and production ready! Set it up by using the qwen/qwen3.6-plus slug, and enjoy a 35% discount on OpenRouter: https://twitter.com/OpenRouter/status/2041897440824184977/photo/1
中文: Qwen3.6-Plus 免费试用已结束，现已上线并完成制作! 使用 qwen/qwen3.6 + 的 slug 进行设置，享受 OpenRouter 35% 的折扣:
2026-04-08 15:14:21
OpenRouter
RT @OpenRouter: Uptime charts for two of the top closed-source models on OpenRouter Don't risk your uptime on single-vendor inference! htt…
中文: RT @OpenRouter:OpenRouter 上两款顶级闭源机型的正常运行时间图表 不要在单次风向推断上冒冒正常运行风险!嗯......
2026-04-08 15:01:45
OpenRouter
RT @PhalaAfrica: Big milestone 👇 ~5B tokens processed confidentially on @OpenRouter with @PhalaNetwork 💪 Top models: 🥇 Kimi K2.5 2B 🥈 Qw…
中文: RT @PhalaAfrica:重大里程碑 👇 ~5B 令牌在 @OpenRouter 上通过 @PhalaNetwork 进行保密处理 💪 顶级模特: 🥇 基米 K2.5 2B 🥈 ..
2026-04-08 14:09:49
OpenRouter
You can now access Claude Opus 4.6 Fast using the new model slug in Claude Code, OpenCode, and all your favorite apps! Just set your model to: anthropic/claude-opus-4.6-fast Verified by our metrics as >2x faster: https://twitter.com/OpenRouter/status/2041710547163635956/photo/1
中文: 现在，您可以使用新型号的 slug 在 Claude Code、OpenCode 以及所有您喜爱的应用程序中访问 Claude Opus 4.6 Fast! 只需将您的模型设置为:antropic/claude-opus-4.6-fast 以 >2x 更快的指标验证:
2026-04-08 02:51:42
OpenRouter
GLM-5.1 from @Zai_org is live on OpenRouter! GLM-5.1 shows a strong jump in long horizon task completion end to end. The model works independently to plan, execute, iterate, and improve upon its work throughout the task, delivering high quality results.
中文: @Zai_org 的 GLM-5.1 在 OpenRouter 上直播! GLM-5.1 显示长地平线任务完成从头到尾的强劲跃升。该模型独立工作，负责在整个任务中对工作进行规划、执行、迭代和改进，从而实现高质量的成果。
2026-04-07 16:18:43
OpenRouter
RT @Altimor: Okay this one seems real. First time ever an OSS model beats Sonnet 4.6(!!) on our evals. Now begins vibe testing, but this is…
中文: RT @Altimor:好吧，这个看起来真实。首次有OSS型号击败Sonnet 4.6(!!)在我们的椭圆形上。现在开始进行氛围测试，但这就是......
2026-04-06 20:35:03
OpenRouter
New: view, replay, and remix previous prompts right from OpenRouter → Auditing: review the quality of outputs → Prompt iteration: refine prompts to improve outputs → Model comparison: replay the same input across different models How to enable it 👇 https://twitter.com/OpenRouter/status/2041193323030089751/photo/1
中文: 新增:从 OpenRouter 右查看、回放和重新混音先前提示 → 审计:评估产出的质量 → 快速迭代:优化提示以改进输出 → 模型对比:在不同模型中重放相同的输入 如何启用它 👇
2026-04-06 16:36:26
OpenRouter
RT @alexatallah: Redline is now a Claude Code plugin! - Unlike other review plugins, it lets the model decide when to automatically review…
中文: RT @alexatallah:Redline 现已是一款 Claude Code 插件! - 与其他评论插件不同，它让模型决定何时自动审核......
2026-04-06 00:44:34
OpenRouter
RT @jpidala: Qwen 3.6 Plus is an incredible model. Well done to the @Alibaba_Qwen team. It blows GPT-5.4-Codex out of the water for agentic…
中文: RT @jpidala:Qwen 3.6 Plus 是一款出色的型号。对@阿里巴巴_Qwen团队做得很好。将GPT-5.4-Codex从水中吹出，用于进行特效操作。
2026-04-05 18:39:48
OpenRouter
We’re excited to have @jjacky joining us soon! Give him a follow to keep up with all things OpenRouter developer news.
中文: 我们很高兴 @jjacky 很快加入我们!给他一个后续消息，以跟上OpenRouter开发者新闻的一切。
2026-04-05 18:01:01
OpenRouter
Qwen 3.6 Plus from @Alibaba_Qwen is officially the first model on OpenRouter to break 1 Trillion tokens processed in a single day! At ~1,400,000,000,000 tokens, it’s the strongest full day performance of any new model dropped this year. Congrats to the Qwen team! https://twitter.com/OpenRouter/status/2040239467865489874/photo/1
中文: @Alibaba_Qwen 的 Qwen 3.6 Plus 正式成为 OpenRouter 上首个在单日内完成 1 个 Trillion 代币的型号! 拥有约1400万枚代币，是今年所有新机型中表现最强劲的全天业绩。恭喜Qwen团队!
2026-04-04 01:26:09
OpenRouter
Gemma 4 from @GoogleDeepMind has hit 2.5B tokens so far: Two flavors: 31B dense, & 26B MoE (running 5x faster than the dense version now!) 256K context • native function calling • multimodal • configurable thinking • 140+ languages Try the 26B MoE: https://openrouter.ai/google/gemma-4-26b-a4b-it
中文: @GoogleDeepMind 的 Gemma 4 迄今已达到 2.5 亿 美元代币: 两种口味:31B 浓密、高密度、26B MoE(比现在的浓密版本快5倍!) 256K 语境 • 原生函数调用 • 多模态 • 可配置思维 • 140 多种语言 试试26B MoE:
2026-04-04 01:08:10
OpenRouter
Gemma 4 from @GoogleDeepMind has hit 2.5B tokens so far: It comes in two packages: 31B dense, & 26B MoE (running 5x faster than the dense version now!) 256K context • native function calling • multimodal (text + image) • configurable thinking mode • 140+ languages. Try…
中文: @GoogleDeepMind 的 Gemma 4 迄今已达到 2.5 亿 美元代币: 它有两种封装:31B 密度和高密度，即26B MoE(比现在的密集版本运行速度快5倍!) 256K 语境 • 原生函数调用 • 多模态(文本 + 图像) • 可配置思维模式 • 140 多种语言。 试试......
2026-04-04 01:05:49
OpenRouter
RT @BloomOne: I did a double blind test before confirming this. Claude Code audited a plan twice, which I also had analyzed by Qwen3.5 fr…
中文: RT @BloomOne:我做了双盲测试，之后才确认了这一说法。 克劳德·法尔曾对一项计划进行了两次审计，我也曾对Qwen3.5进行了分析。
2026-04-03 20:56:01
OpenRouter
New benchmark visualizations from @DesignArena are now live: 3D, Website building, SVG, & more 🕸️ Use the dropdown in the upper-left to compare reasoning levels on a single model https://twitter.com/OpenRouter/status/2040126207149449388/photo/1
中文: @DesignArena 的新基准可视化现已上线:3D、网站构建、SVG 和 & 更多 🕸️ 使用左上角的下拉法比较单个模型的推理水平:
2026-04-03 17:56:06
OpenRouter
Uptime charts for two of the top closed-source models on OpenRouter Don't risk your uptime on single-vendor inference! https://twitter.com/OpenRouter/status/2039734706061860980/photo/1
中文: OpenRouter 上两款顶级闭源模型的正常运行时间图 不要在单次供应商推断上冒冒正常运行风险!
2026-04-02 16:00:25
OpenRouter
Use Fusion to get the best possible response across models without violating your org's data policies Includes support for ZDR (zero data retention): https://openrouter.ai/labs/fusion https://twitter.com/OpenRouter/status/2039732721598230550/video/1
中文: 使用 Fusion 在不违反您的品牌数据策略的情况下，在各型号之间获得最佳响应 支持ZDR(数据保留率为零):
2026-04-02 15:52:31
OpenRouter
RT @Alibaba_Qwen: Qwen3.6-Plus is officially live on @OpenRouter .🚀 Go try it out and let us know what you think. Can't wait to hear your…
中文: RT @Alibaba_Qwen:Qwen3.6-Plus 正式上线 @OpenRouter。EE0 试试吧，告诉我们你的想法。 迫不及待想听你的......
2026-04-02 15:43:04
OpenRouter
Qwen 3.6 Plus from @Alibaba_Qwen is live now on OpenRouter, for free! Prompts and completions are not retained during this period. Use it in all your favorite apps! 1M context, multimodal, agentic. https://twitter.com/OpenRouter/status/2039727905320952068/photo/1
中文: @阿里巴巴的Qwen 3.6 Plus现已免费在OpenRouter上线! 在此期间，提示和完成均不得保留。在您喜欢的所有应用中使用! 1M 上下文，多式联运，特化。
2026-04-02 15:33:23
OpenRouter
New: you can now find knowledge cutoff dates for LLMs in our /models API: https://twitter.com/OpenRouter/status/2039522490821845247/photo/1
中文: 新增:现在您可以通过我们的/models API找到LLM的知识截止日期:
2026-04-02 01:57:08
OpenRouter
Arcee’s latest model, Trinity Large Thinking is live now on OpenRouter! It is a 400B total 13B active model with powerful agentic performance, free in @openclaw for the first 5 days! https://twitter.com/OpenRouter/status/2039369849441497340/photo/1
中文: Arcee 的最新模特《Trinity Ralge Thinking 现已上线》在 OpenRouter 上直播! 它是一款400B的13B活跃型号，具有强大的代理性能，前5天免费在@openclaw上使用!
2026-04-01 15:50:36
OpenRouter
RT @Teknium: We are now the 6th largest ai app in the world on Open Router and growing! https://twitter.com/Teknium/status/2039296601810976973/photo/1
中文: RT @Teknium:我们现已成为Open Router上全球第六大i应用，并不断发展壮大!
2026-04-01 15:13:21
OpenRouter
We asked ourselves: what if the best UI era never ended? Introducing OpenRouter's new look, inspired by the golden age of the web 🌐 ✨ Under construction. Always. 🚧 https://twitter.com/OpenRouter/status/2039359031534653720/photo/1
中文: 我们问自己:如果最好的用户界面时代从未结束，会如何? 推出OpenRouter的全新外观，灵感源自网络的黄金时代🌐 ✨ 正在施工中。永远。🚧
2026-04-01 15:07:37
OpenRouter
RT @matvelloso: Every time someone asks me which model I'm using to code I find that puzzling. You use one model?
中文: RT @matvelloso:每次有人问我用哪个模型编写代码时，我都会觉得这令人费解。你使用一个模型吗?
2026-03-31 19:39:59
OpenRouter
RT @jasonth0: i've been doing this manually between opus and gpt for weeks. glad someone finally automated the couples therapy
中文: RT @jasonth0:我已经连续数周在 opus 和 gpt 之间手动完成此操作。很高兴终于有人实现了夫妻治疗的自动化
2026-03-31 18:46:21
OpenRouter
RT @NewcomerMedia: @Wing_VC @mintlify @DustHQ @llama_index @crewAIInc @e2b @crosbylegal @arcade_ai The mid stage startups that topped our l…
中文: RT @Newcomer媒体:@Wing_VC @mintlify @DustHQ @llama_index @crewAIInc @e2b @crosbylegal @arcade_ai 中端初创企业
2026-03-31 16:03:27
OpenRouter
OpenRouter is on the 2026 Enterprise Tech 30. Big thanks @Wing_VC and @EricNewcomer! https://twitter.com/OpenRouter/status/2039008691350089822/photo/1
中文: OpenRouter 是 2026 年企业级 Tech 30 的公司。非常感谢 @Wing_VC 和 @EricNewcomer!
2026-03-31 15:55:29
OpenRouter
RT @alexatallah: LLM neurodiversity really works for deep research tasks! This agent’s responses are consistently ranked higher by Opus an…
中文: RT @alexatallah:LLM神经多样性确实适合深度研究任务! 该代理的回复率始终高于 Opus an...
2026-03-31 15:41:44
OpenRouter
New public experiment: Model Fusion Use multiple models, analyze outputs, and fuse the results for a response that every Deep Research agent preferred to its own, in our testing. No subscription needed at all. https://twitter.com/OpenRouter/status/2038997156347179157/photo/1
中文: 新公共实验:模型融合 使用多个模型，分析输出结果，并融合结果，以便在我们的测试中实现每个深度研究代理都偏好的响应。 完全无需订阅。
2026-03-31 15:09:39
OpenRouter
RT @Alibaba_Qwen: Our new model is now live on OpenRouter for an early preview, go give it a try! Looking forward to your feedback~😎
中文: RT @Alibaba_Qwen:我们的新机型现已在 OpenRouter 上实时上线，提前预览，请尝试一下!期待您的反馈~😎
2026-03-31 00:50:07
OpenRouter
Qwen 3.6 Plus Preview from @Alibaba_Qwen is live now for free for a limited time on OpenRouter! During this free period, prompts and completions will be collected and may be used to improve the model. https://twitter.com/OpenRouter/status/2038701599175196715/photo/1
中文: @Alibaba_Qwen 的 Qwen 3.6 Plus 预览版现已限时免费上线，可在 OpenRouter 上免费获取! 在此期间，将收集提示和完成内容，并可用于改进模型。
2026-03-30 19:35:13
OpenRouter
Updates on Hunter Alpha: - Full support for Hunter (and Healer) in OpenClaw! - Coding performance is greatly improved after we resolved a bug with interleaved thinking. Hunter is more stable and capable now.
中文: 关于Hunter Alpha的更新: - 在 OpenClaw 中全力支持 Hunter(和 Healer)! - 通过间解思维解决一个漏洞后，编码性能得到了极大提升。亨特现在更加稳定且有能力。
2026-03-12 14:40:52