Tag
PixelCrew is an AI-powered design platform that uses a crew of specialized agents to coordinate on design briefs, producing research, creative direction, wireframes, and production-ready HTML with a design system. It's available in alpha on Product Hunt, free to use with your own OpenRouter key.
A user shares observations about the new 'Union stealth' model on OpenRouter, comparing its performance to Qwen models and speculating it could be a Qwen4 MoE variant with 256k context and a training cutoff in late 2025.
The tweet reports that GPT-6 Astra had the highest spending on OpenRouter last week, while GPT-5.6 Luna used the most tokens, leading by a wide margin.
CrofAI, an AI inference provider claiming cheap tokens, was exposed as an OpenRouter wrapper that routed requests to cheaper models at a high markup, leading to wire fraud allegations and the company's sudden shutdown.
This article outlines the API pricing and available providers for the Fugu Ultra v2 AI model, hosted on OpenRouter.
The article discusses issues with OpenRouter's automatic provider routing, such as inconsistent model behavior across different backends, and suggests using options like provider.only for better control.
This article outlines the pitfalls of using OpenRouter for accessing open-source AI models, based on the author's experience with 18 million messages, including significant benchmark variations across providers and issues with vision models.
The author discusses their experience with AI models like GLM 5.3 Flash and DeepSeek V4 Flash on Open Router, finding them unreliable compared to Claude or Devin, and seeks a trustworthy agentic harness for effective model handling.
A Python and TypeScript library for downloading LLM catalogs and building pipelines to filter and select models based on criteria like price, latency, and benchmarks.
The tweet shares an observation on using OpenRouter rankings to monitor AI trends, noting significant year-over-year growth in token demand.
Release of llm-openrouter version 0.7.1, a development tool for interacting with OpenRouter, with sponsorship from Portnox on AI visibility management.
A team lead discovered that a coworker's AI agent was consistently repeating negative framing in handoff messages, revealing how agents absorb human tone and contributing to the coworker's termination after a pattern of issues.
OpenRouter's weekly token usage has surged from 4.6 trillion a year ago to 113 trillion, with a doubling in the past month, indicating significant growth in the AI platform's adoption.
The post highlights the exponential growth in AI token usage, such as OpenRouter's 25x weekly increase, and its potential to drive double-digit GDP growth, while noting that many investors and the public do not comprehend this compounding trend.
Closed models from Google and OpenAI have taken the second and third positions on OpenRouter, a platform that traditionally favored cheaper Chinese open-weight models.
The post highlights how discounting GPT 5.6 models on OpenRouter led to a 13.8x increase in token usage, illustrating the Jevons Paradox where efficiency gains result in higher total resource consumption.
Ant's Ling team has released Ling-3.0-flash-Fin, a finance-enhanced AI model designed for financial workflows, with free access on OpenRouter for one month and plans to open-source the weights.
Ox Alpha, based on GLM-5.3 Flash AA, is announced at one-hundredth the price of frontier models, powered by Chinese chips, and has achieved nearly 20% weekly token share on OpenRouter.
Speko is a voice-based tool that integrates with OpenRouter, recently launched on Product Hunt for voice interactions.
A video visualizes the top 20 AI models by weekly token usage on OpenRouter from December 2024 to August 2026, showing a shift from US to Chinese labs dominating the leaderboard.