惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Microsoft Azure Blog
Microsoft Azure Blog
WordPress大学
WordPress大学
小众软件
小众软件
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
V
V2EX
Hugging Face - Blog
Hugging Face - Blog
美团技术团队
博客园 - 三生石上(FineUI控件)
Last Week in AI
Last Week in AI
酷 壳 – CoolShell
酷 壳 – CoolShell
博客园 - Franky
Microsoft Security Blog
Microsoft Security Blog
Y
Y Combinator Blog
A
About on SuperTechFans
The GitHub Blog
The GitHub Blog
U
Unit 42
H
Hackread – Cybersecurity News, Data Breaches, AI and More
云风的 BLOG
云风的 BLOG
IT之家
IT之家
MyScale Blog
MyScale Blog
V
Visual Studio Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
I
InfoQ
博客园 - 司徒正美

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
Neuralwatt Cloud | Neuralwatt Cloud
Neuralwatt Inc. · 2026-06-22 · via Hacker News - Newest: "AI"

Neuralwatt Cloud

Run Inference with Real Visibility
into Power, Cost, and Efficiency

The first AI inference API with energy-based pricing. Know exactly what your AI costs — in dollars and kilowatt-hours.

Use Neuralwatt Cloud as a hosted service, or bring Neuralwatt Deploy into your own data center.

$5/kWh

Energy-Based Pricing

<50ms

Median Time to First Token

Try it now

Send a prompt and see energy-aware inference in action.

Industry First

Inference Priced by Energy Consumed

Token-based pricing hides the true cost of AI inference. We're changing that. Pay per kilowatt-hour and know exactly what resources your AI workloads consume.

Transparent

See energy consumption per request. No hidden costs, no opaque token multipliers.

Predictable

Energy costs are consistent. No surprises from model-specific pricing variations.

Efficient

Optimize your AI workloads. Compare energy efficiency across models and make informed decisions.

Compare energy vs token pricing

Three pillars that define every layer of our platform.

Included Free

Energy Reporting

Every customer gets real-time energy metrics. Know exactly what your AI workloads consume.

  • Per-request energy metrics
  • Dashboard with usage trends
  • Model efficiency comparisons

Performance

State-of-the-art inference powered by vLLM with tensor parallelism, continuous batching, and advanced KV caching.

  • As low as 15ms time to first token
  • High throughput at scale
  • Multi-GPU tensor parallelism

Efficiency

More intelligence per kilowatt-hour. Optimized infrastructure for maximum compute efficiency.

  • 40% more energy efficient
  • Energy-aware scheduling
  • Optimized GPU utilization

Multi-Model API

Access multiple LLMs through a single API. Switch models seamlessly without managing separate connections.

OpenAI Compatible

Drop-in replacement for OpenAI APIs. Just change your base URL and you're ready to go.

The Neuralwatt Platform

Three integrated capabilities for high-performance, energy-efficient AI — from the data center to the API.

Neuralwatt Cloud

YOU ARE HERE

Hosted Inference Service

The first AI inference service with energy-based pricing. OpenAI-compatible API with real-time energy transparency per request.

Neuralwatt Deploy

On-Premise Optimization

Bring Neuralwatt's energy optimization directly into your data center. Full control over your hardware, security, and power consumption.

Neuralwatt Optimize

Power Optimization Engine

Intelligent layer between AI workloads and GPUs that continuously tunes power consumption in real time with less than 0.1% performance overhead.

Learn more about Neuralwatt's full platform

Featured Models

Access the latest open-source models from leading providers. All with OpenAI-compatible APIs.

View all models

Start with Energy-Transparent AI

Get started with $5 in free credits. Pay per kWh or per token — your choice. Real-time energy reporting included with every account.

Enterprise & Dedicated Inference

Need dedicated GPU capacity, custom SLAs, or on-premises deployment? Our enterprise solutions offer guaranteed performance with full energy transparency.

  • Dedicated GPU infrastructure
  • SLA guarantees up to 99.9%
  • Volume pricing & custom models
Contact Enterprise Sales