ai reasoning model pricing per token

Published on November 10, 2026 at 12:03 PM Tech Artificial Intelligence “‘Ram Altman’: He creates a script that alerts OpenAI’s boss to the RAM idling in your PC” Funny 3 min Lisa Imperatrice 3 min 3 min Lisa Imperatrice Don't see this ad anymore Zen reading Summarize the article Article summary Summary by AI, verified by Numerama ? We generate a summary of the article for you using AI and check it to make sure there are no errors, thereby guaranteeing the

There are indications that the reasoning capabilities of Anthropic’s AI model “Claude Opus 5.5” may have declined sharply around November 3, 2026. Developer Shane Melaugh analyzed approximately 1,400 usage records for the AI programming assistant “Claude Code” and found significant changes in the wording used to express the AI’s reasoning and in the way it approached tasks, despite the model name remaining unchanged. is Opus 5.5 nerded?I just had Gemini 4

On November 10, Ant Lingbo Technology open-sourced the tactile foundation model LingBot-Touch On November 10, Ant Lingbo Technology open-sourced the tactile foundation model LingBot-Touch, filling a critical gap in tactile perception for robot brains. The model was pre-trained on nearly 5,000 hours of real tactile data and covers three mainstream sensing principles: magnetic tactile sensing, vision-based tactile sensing, and piezoresistive sensing. It can

Google Deepmind's Genie 4 puts a modern spin on agent designs that predate LLMs Maximilian Schreiner View the LinkedIn Profile of Maximilian Schreiner Oct 27, 2026 Google Key Points Google Deepmind has introduced Genie 4, an interactive world model that calculates environments frame by frame in real time and, for the first time, directly generates matching background audio and character dialogue. Gemini models steer events in the background, planning multi

Alibaba's latest Qwen models routed some requests through company servers, researchers find Manuel Uth Oct 27, 2026 Nano Banana Pro prompted by THE DECODER AI News Without the Hype – Curated by Humans Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section. Subscribe now { "@context": "https://schema.org", "@type": "NewsArticle",

OpenAI says it stopped a campaign to steal its models' reasoning, but the trick still worked on Azure Maximilian Schreiner View the LinkedIn Profile of Maximilian Schreiner Oct 1, 2026 GPT-Image-2 prompted by THE DECODER AI News Without the Hype – Curated by Humans Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section. Subscribe

Anthropic says it cut Claude reasoning token theft by up to 99% in fight against industrial-scale distillation Manuel Uth Oct 13, 2026 Anthropic is battling large-scale distillation attacks on its Claude models. In these attacks, companies systematically copy an AI model's capabilities to train their own, smaller models. Anthropic says its new defenses have cut the volume of extracted reasoning tokens, the model's internal chain-of-thought steps, by 90 to

Chinese AI model Kimi K3.1 Pro is closing in on Anthropic's Claude Opus 5.5 Matthias Bastian View the LinkedIn Profile of Matthias Bastian Oct 23, 2026 Moonshot AI Key Points Chinese AI company Moonshot AI has released Kimi K3.1 Pro, which jumped to fourth place on the Artificial Analysis Intelligence Index with 55 points, just behind Claude Opus 5.5. The model shows major gains in agentic tasks, coding, and 3D modeling. The parameter count stays at 2.8 tr

OpenAI's Astra becomes the main target for Chinese AI labs after Anthropic tightens its defenses Maximilian Schreiner View the LinkedIn Profile of Maximilian Schreiner Oct 29, 2026 Chinese AI labs are now mainly tapping OpenAI's most powerful model, GPT-6 Astra, instead of Anthropic's Claude. According to The Information, DeepSeek and Moonshot AI leaned heavily on Astra's outputs to train their latest models. People familiar with the matter say this includ

OpenAI calls Astra its most dangerous model yet - watching what it does is only getting harder Maximilian Schreiner View the LinkedIn Profile of Maximilian Schreiner Sep 2, 2026 Nano Banana Pro prompted by THE DECODER AI News Without the Hype – Curated by Humans Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section. Subscribe no

OpenAI starts with infrastructure robots but aims for "everyone having a personal robot doing anything they need" Matthias Bastian View the LinkedIn Profile of Matthias Bastian Jun 1, 2026 AI News Without the Hype – Curated by Humans Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section. Subscribe now { "@context": "https://sche

Baidu releases ERNIE 5.5 Flash Base with 280 billion parameters as an open-source foundation model Matthias Bastian View the LinkedIn Profile of Matthias Bastian Nov 5, 2026 Baidu's AI development is still alive, but most of the work is on you. The Chinese company has released ERNIE-5.5-Flash-Base, an open foundation model that ships deliberately without fine-tuning or post-training. Developers are expected to decide for themselves where to take the model.

Meta's Muse agent gives every user a full cloud computer running Ubuntu Linux Matthias Bastian View the LinkedIn Profile of Matthias Bastian Sep 25, 2026 GPT-Image-2 prompted by THE DECODER Ask about this article… Search Every Muse user gets a free, full-fledged computer in the cloud with its own Ubuntu Linux image. Every Muse user gets a free, full-featured computer in the cloud, according to David Singleton, VP of Engineering at Meta Superintelligence La

Reported by Synced In multi-stage reasoning, local misjudgments can become premises for subsequent judgments and continue to influence later steps. This problem is particularly prominent in empathetic speech dialogue: perception, psychological-state inference, and response generation are closely interconnected, and early biases may ultimately lead to misunderstandings of the speaker’s needs and inappropriate responses. Even if the subsequent analysis is lo

State propaganda in some Chinese AI models is only "a thin layer" that fine-tuning can strip away Jonathan Kemper View the LinkedIn Profile of Jonathan Kemper Nov 7, 2026 Nous Research Key Points Nous Research fine-tuned Alibaba's Qwen3.8-27B to remove Chinese state propaganda from the model's responses. Supervised fine-tuning on 53 million tokens cut the propaganda rate from 22 to under one percent without hurting the model's general capabilities. Accordi

Zhidx (WeChat public account: zhidxcom) Author | ZeR0 Editor | Moying Zhidx reported on November 5 that the second International Engineering Intelligence Conference of the 2026 World Laureates Forum was held recently. At the conference, Tao Mei, a foreign member of the Canadian Academy of Engineering and founder and CEO of Zhixiang Yuanyi (HiDream.ai), delivered a speech proposing the construction of agentic omnimodal world models (Agentic Omnimodal World

Zhidx (WeChat official account: zhidxcom) Author | Li Shuiqing Editor | Yun Peng Zhidx reported on November 6 that OpenAI today unveiled a new model, GPT-6 Cyber, focused on security research. The model achieved significant improvements over GPT-5.6 Cyber on key cybersecurity benchmarks. In the ExploitGym security test, GPT-6 Cyber scored 48.5%, compared with 32.1% for GPT-5.6 Cyber, a relative improvement of 51%. ▲OpenAI posted an announcement on social p

November 5: Alibaba Releases the “2026 AI for Good Action Report” On November 5, Alibaba released the “2026 AI for Good Action Report,” revealing its latest efforts to develop responsible AI and use AI to create social value. The report presented 26 cases spanning education, healthcare, environmental protection, scientific research, and other fields. Sustainable data center development and the achievements of “AI + healthcare” innovation attracted consider

It should be noted that this does not mean that someone who cannot talk like a human must be human, nor does it mean that someone who can talk like a human definitely is not an AI... Cheng Qian, from the Office QbitAI | QbitAI WeChat Official Account Recently, I noticed that human writing ability had already begun evolving in reverse. Why call that evolution? With AI around, writing has become faster and faster; turning an idea into a finished piece can so

We’re releasing gpt-oss-120b and gpt-oss-20b—two state-of-the-art open-weight language models that deliver strong real-world performance at low cost. Available under the flexible Apache 2.0 license, these models outperform similarly sized open models on reasoning tasks, demonstrate strong tool use capabilities, and are optimized for efficient deployment on consumer hardware.