bnishit

Connect apps to 300+ AI models through OpenRouter's OpenAI-compatible API — model discovery, image generation, multimodal chat (text, images, PDFs), exact per-generation cost tracking, provider routing with fallbacks, tool calling with safety limits, structured output validation, free-model filtering, starter templates (Next.js, Express), asset workflows (icons, OG images), production playbooks, and verification scripts. Use when an agent needs to add or debug OpenRouter usage, build a model picker, proxy `/api/v1/models`, `/api/v1/models/user`, `/api/v1/providers`, or `/api/v1/generation`, send image or PDF content to `/api/v1/chat/completions`, generate images through OpenRouter, build icon or OG image flows, parse OpenRouter responses, inspect generation cost after the fact, add Next.js or Express server routes, validate structured outputs, run smoke tests, verify current docs against OpenRouter before coding, or wire model or provider fallbacks into a server or UI.