Reading up on OpenRouter

OpenRouter offers a unified API for hundreds of AI models, with integration options via raw API, typed Client SDKs, or higher‑level Agent SDK for building tool‑enabled agents.

OpenRouter provides a unified API to browse, filter, and retrieve details for over 400 AI models, including pricing, capabilities, and provider info.

Several vendors now offer intelligent model routers that automatically select the cheapest sufficient LLM per task, promising 20-30% cost savings, a trend expected to become table stakes.

OpenRouter's Fusion plugin runs a panel of models in parallel, judges their responses for consensus and contradictions, and feeds structured analysis back to the calling model for a better final answer.

OpenRouter's Fusion, which synthesizes outputs from multiple language models via a judge model, outperformed individual frontier models including GPT-5.5 and Claude Opus 4.8 on deep research tasks, with a budget panel achieving near-frontier performance at half the cost.

Closed AI frontier labs (Anthropic, OpenAI) will form an oligopoly selling premium intelligence to high-value users like coding agents, while open models will dominate broader commodity AI use across the economy.

Alphabet's investment arm backs OpenRouter, a platform that helps companies select among hundreds of AI models for various tasks, raising $113 million.

OpenRouter ranks live LLM usage by tokens and spend, showing DeepSeek, Anthropic, and others dominating across general, agent, and code tasks.

Running local LLMs on Apple Silicon is not cheaper than using cloud APIs like OpenRouter when factoring hardware, electricity, and speed costs.

Running local LLMs on Apple Silicon costs about 3x more per million tokens than using OpenRouter, and also runs slower.

Sitegeist is a browser-based AI assistant that lets users automate web tasks, extract data, and build reusable skills while keeping data local and offering flexible AI model choices.

The viral claim that Anthropic loses $5,000 per Claude Code Max subscriber confuses retail API prices with actual inference costs, which are roughly 10x lower.

OpenPencil is an open-source, AI-native design editor that opens .fig files, offers a programmable CLI and Vue SDK, and supports real-time collaboration and MCP integration.

Stripe previewed a billing feature that lets AI companies track token usage, pass through costs, and automatically apply a profit markup on underlying model fees.

MiniMax researcher Olive Song reveals how they debug RL training, handle model hacking, and prioritize alignment and engineering discipline in open-weight model development.

Craft Agents is an open-source agent orchestration platform that connects to any API, MCP server, or local file via natural language, with a built-in browser, multimodal model support, and session-based workflows.

Benchmarking LLMs on actual task-specific prompts can find cheaper alternatives that match performance, saving 5-10x on API costs.

TanStack AI is an open-source TypeScript SDK that provides a provider-portable, protocol-first layer between user interfaces and AI models without requiring a hosted gateway.

An empirical study of over 100 trillion LLM tokens on OpenRouter reveals rising open-weight adoption, dominant roleplay and coding tasks, and a 'Glass Slipper' retention effect.