TLDR: Reasoning models → keep detail on auto or high, control cost with reasoning effort Non-reaso... - 惯性聚合

推荐订阅源

cs.CL updates on arXiv.org

Recent Announcements

Google Developers Blog

Secure Thoughts

大猫的无限游戏

博客园 - 【当耐特】

cs.CV updates on arXiv.org

博客园 - 聂微东

The Cloudflare Blog

阮一峰的网络日志

人人都是产品经理

Privacy International News Feed

Kaspersky official blog

The Blog of Author Tim Ferriss

Attack and Defense Labs

Threat Intelligence Blog | Flashpoint

aimingoo的专栏

Simon Willison's Weblog

cs.AI updates on arXiv.org

Netflix TechBlog - Medium

Proofpoint News Feed

freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More

Tor Project blog

Security Affairs

Proofpoint News Feed

博客园 - 三生石上(FineUI控件)

博客园 - Franky

Cyber Attacks, Cyber Crime and Cyber Security

Exploit-DB.com RSS Feed

美团技术团队

Recent Commits to openclaw:main

Security @ Cisco Blogs

LINUX DO - 热门话题

Know Your Adversary

Lohrmann on Cybersecurity

Full Disclosure

OpenRouter(@OpenRouterAI)

OpenRouter (@OpenRouter) on X OpenRouter (@OpenRouter) on X OpenRouter (@OpenRouter) on X Use it now: https://t.co/yrkHFKgtBK Read more: https://t.co/SVCrJIH3x9 Grok 4.5 is live now on OpenRouter! Cursor’s contributions have helped make @SpaceXAI’s model fron... Use Grok 4.5 from @SpaceXAI the moment it goes live, with no code change. ~x-ai/grok-latest always ... New: one-click ZDR (zero-data retention) in the Chatroom Compare models side-by-side with full priv... So what actually moves the bill? Reasoning effort, by a wide margin. Detail swung accuracy 2 to 17 ... We benchmarked 1,730 visual reasoning questions across 5 models to test a common cost-saving trick: ... V4 also broke DeepSeek away from the other Chinese models. At 6.6T weekly tokens it now runs well a... Full breakdown across 457 trillion tokens of request data here: https://t.co/sV83QDrRCI DeepSeek doubled its token share on OpenRouter in six months, going from 9% in January to 18% by Jun... More about the MCP: https://t.co/1O8czSPLGz Get started here: https://t.co/PYkilNr1At Saving 24x on inference costs with comparable quality, using the OpenRouter MCP: Rube Goldberg machine built with Fable 5, for $4.44 👀 Prompt available here: https://t.co/zlLXo01J... Try it at https://t.co/Q4Ql4Dp0qX Claude Fable 5 from @Anthropic is back on OpenRouter! Anthropic is redeploying it globally with new... Open-weight provider meta-benchmarking, run and published continuously by OpenRouter. Powers our to... @AnthropicAI Always stay on the latest Sonnet by using ~anthropic/claude-sonnet-latest in your API c... Read more from @AnthropicAI https://t.co/yvNWET0S1R Try it: https://t.co/WxKkwssTJY Claude Sonnet 5 is rolling out on OpenRouter with a promo price: $2/M in and $10/M out! It boosts a... Tip: OpenRouter continuously runs GPQA and TAU-Bench on most open-weight models and publishes the re... More about AutoExacto: https://t.co/x9tJDRDBst Four open-weight models have crossed into territory where they are powering real agentic pipelines. ... In this OpenRouter MCP demo, your agent finds the best model at design: 1. Pulls the top design mod... More info about the new MCP: https://t.co/1O8czSPLGz Example of how to use the OpenRouter MCP to build a model council. Tuned for your codebase and usec... Learn how to enable ZDR: https://t.co/1xtHh9Nu8x xAI + Zero Data Retention, now live on OpenRouter. 🔒 Available across Grok 4.3, 4.20 and Build 0.1... See the live provider rankings here: https://t.co/6dix5xd1cz TIP 💡@Zai_org GLM-5.2 providers are working on faster and faster inference! Today's new endpoints i... One UI. Every model. 👇 https://t.co/HiHmNhwmST Interface + inference, in one place. @OpenWebUI now runs on OpenRouter. Give your team one chat in... Official OpenRouter MCP: help your agents pull live data about model pricing, benchmarks, popularity... The model performance rankings come from our new Benchmarks API, allowing your agent to query live b... Pick, price, test, and wire in a model in under a minute Connect in two commands: claude mcp add -... Introducing the OpenRouter MCP, live model intelligence right inside your agent Your agent builds a... Read more: https://t.co/IPGqVXrPUG Try it: https://t.co/ElyMWqX7y9 Fugu Ultra by @SakanaAILabs is live on OpenRouter! Excited to see more multi-model systems pushing ... Browse every image model: https://t.co/k3txKFP3Ei Read the docs: https://t.co/o2VCkW6CKi Full announcement here: https://t.co/D3yl0Aey8z Introducing a new, dedicated Image API, including typed dynamic capabilities. Unified access to 30+... Access all the providers for GLM 5.2 in one spot. Including one serving at over 125 TPS: https://t.... More LLM data insights on our blog: https://t.co/t419GbaBhq Here are version uptake timelines for the two model families, GLM and DeepSeek GLM 5.2 vs DeepSeek V4: share of tokens on OpenRouter GLM 5.2 has had a very fast uptake relative t... Humans. Agents. Same checkout. Excited to partner with @coinbase to bring stablecoin payments to ou... Tip 💡: if you have @1Password installed, OpenRouter will detect it and help you save your API keys

TLDR: Reasoning models → keep detail on auto or high, control cost with reasoning effort Non-reaso...

OpenRouter ( · 2026-07-08 · via OpenRouter(@OpenRouterAI)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。