Developer Tools4 weeks ago
FlexInference: Drop your AI costs today
Route your LLM API requests across multiple providers to cut costs and meet latency targets.
Aperswal · HN
Made a Free LLM Router
The full gallery
Tech stack
60 projects
Route your LLM API requests across multiple providers to cut costs and meet latency targets.
Aperswal · HN
Made a Free LLM Router
Test large model API relay stations for consistency and authenticity with official versions.
@nodeloc_cc · X
🌈 7月，你好，MODELOC上线算力池。 MODELOC自上线以来，已检测2000余次，覆盖600+中转站，为众多AI用户提供的使用参考。 MODELOC近期进行了改版，上线了算力池及市场。 加入算力池 查看帖子： 用 MODELOC 便宜地调各家大模型：一次讲清它的价格体系
AI-powered travel planning workbench for creating custom itineraries.
Routewise-AI — 旅行规划工具（免费），基于 GPT-5.6 大模型
One OpenAI-compatible gateway in front of 13 providers. Budgets with hard caps, rate limits, and analytics. Flat subscription, zero token markup.
@tokenrouter · X
Visualize and simulate the BBRv3 congestion control algorithm in your browser.
dilyevsky · HN
BBRv3 for gVisor's netstack, visualized in the browser using WASM
Access 200+ AI models (Claude, GPT, Gemini) through one unified API with automatic failover.
@MixRoute_ai · X
AI fashion photography platform for e-commerce: model swap, flat-lay to on-model, garment recolor, and AI packshots, with pixel-perfect garment preservation.
@8DavideRighini8 · X
Agent-native TypeScript framework that trains and deploys custom ML models on managed GPUs.
@soleil_colza_ · X
Route LLM API traffic through a gateway with built-in cost tracking, latency analytics, and PII redaction.
charltonraven · HN
RavenGate – LLM gateway that redacts PII across SSE chunk boundaries
Get a prepaid API key to access Claude and GPT models unified via one endpoint.
@MesaRelay · X
Using Codex, Claude Code, or Cursor shouldn’t mean juggling provider accounts, API keys, and billing pages. MesaRelay gives coding agents one prepaid API key for Claude + GPT routes—with a hard spending ceiling and per-call usage logs. Try it:
Chat with AI models and visualize conversations as branching diagrams using OpenRouter.
two-sandwich · HN
BixRouter – a non-linear AI chat interface for OpenRouter
Check which network routes and Cloudflare nodes various AI services use.
@0xdeusyu · X
想知道代理是不是真的把每个 AI 站都送到同一个出口？ 答案：并不是。 我做了一个 AI 分流测试： 它会探测 ChatGPT、Sora、OpenAI、Claude、Grok、Anthropic、Perplexity 等 AI 服务，通过读取各站点的 Cloudflare Edge Trace 信息，获取实际访问情况： 出口 IP Cloudflare 边缘节点（colo） HTTP / TLS / WARP 状态 访问延迟 然后根据落地位置进行归组。 这次测试结果： 6 个服务（覆盖 7 个域名）走美国出口。 唯一例外是 Sora，落在东京节点。 也就是说，同一个代理配置下，不同 AI 服务并不一定经过同一个出口。看起来“都能访问”，实际线路、节点和落地点可能完全不同。 整个测试工具纯前端实现，零后端。