7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.

🧠 Train a 64M-parameter LLM from scratch in just 2h!

针对GPT 6.0,V4flash的破甲实验项目

👁️ Review AI generated code and plan changes

AI 大模型世界，把 556 个大模型拟人化成像素小人的可视化站点。进来就能看到此刻谁最聪明、谁最会写代码、谁最便宜、谁刚发布，往下是国内与国外分区的厂商广场、完整的发布时间线和多维排行榜。搜索认模型名、厂商和能力，输入「多模态」会直接列出全部多模态模型。数据取自 Epoch AI、models.dev、LiveBench 与 Hugging Face，每小时自动同步，所有文案由真实数据生成，不调用任何 LLM。Next.js 静态导出，零后端。

Build distributed, production-grade, long-running agents.

Per-turn model & reasoning routing for Codex, driven by Jev (TypeSafe System One): picks the model, thinking depth and speed mode for every turn.

SkillAdam: Better Skills for Your AI Agent🚀 Claude Code/Codex/Cursor 插件，一键进化你的skill

High-performance neural networks engine for web, built on top of TypeGPU

A tiny Claude Code skill that keeps your prompt cache warm during idle sessions, so your next message reads from cache instead of paying full price.

Anyone can predict the future. Almost nobody keeps the receipt. A hash-chained prediction ledger for LLMs — sealed before the answer exists, graded with proper scoring rules.

LinkTokenView（联视未来）国产大模型 Token API 聚合平台，提供 OpenAI 兼容接口，统一调用 DeepSeek v4.1、Kimi、GLM、通义千问 等模型，支持 Token Plan 与 Coding Plan。支持Codex、Claude、Harness、WorkBuddy等各类Agent工具。已上线deepseek-v4.1-flash。