开发者工具1 week ago
ModelGate — cost control for LLM APIs
An LLM gateway for OpenAI, Anthropic, Google and Azure. Every request logged, priced to the token, and audited for waste you can actually recover.
@razdagan3 · X
完整作品展
技术栈
23 projects
An LLM gateway for OpenAI, Anthropic, Google and Azure. Every request logged, priced to the token, and audited for waste you can actually recover.
@razdagan3 · X
使用一个 API 访问和切换多个 LLM 提供商，同时优化推理成本。
justin2025 · Product Hunt
Auriko Trading desk for LLM calls
开源LLM和视频模型的OpenAI兼容API
bingus-bongo · HN
Use GLM-5.3 in Cursor today via tokengo API
追踪100+来源的AI和LLM新闻和模型发布。
jonam21 · HN
KBlip – turns AI/LLM news across 100 sources into daily digest threads
从网站生成 MCP 端点和 llms.txt 文件供 AI 代理集成。
AshHackerNews · HN
AgentReady – MCP server that makes any docs site queryable by AI agents
Modern legal case management platform for plaintiff litigation law firms.
@galbanese91 · X
将LLM调用路由到成本最低的合适模型，保持质量。
george_avila · Product Hunt
IQ Routing Trajectory-aware LLM routing that cuts agent cost
在290万份Form 5500文件中搜索并评分退休计划，找到符合条件的客户。
@401Casey · X
Vibe coding is incredible thank you for the push @TheStalwart & @jxmnop Today I am launching a free tool to help advisors to retirement plans find more clients. Something that previously may have cost them 10-20k/year built and launched for free.
在纽约查找免费法律援助服务，追踪与法律组织的沟通。
@ChaChaChaChiia · X
My first vibe coded project: NYC Legal Aid Finder. This helps you track your communication with organizations that can help you navigate a case and also a guide finder for relevant articles and text based on the case subject. #vibecode #Legalaid #tech #Ai
检测LLM API是否被降智或偷换模型，一键跑6项探针得出结果
cocodot LLM 降智检测 — 免费的 LLM API「降智/偷换模型」在线检测：填入任意 OpenAI 兼容端点的 base_url 和临时 API Key，跑 6 项探针（模型声明、动态题、能力完整性等）生成分项报告；Key 仅用于当次检测、不落库不留存，检测方法[开源](https://github.com/cocodot2026/cocodot-llmprobe)
向Claude、GPT和Gemini提问，获得它们相互审核的共识答案。
@StevenJdotCom · X
One AI makes mistakes. Three catch each other's. AI Consensus runs your prompt through Claude, GPT and Gemini. They work it independently, then critique each other until they reach consensus — handing you an AI audited, combined answer.