Compare AI tools

	Lex A	OpenRouter S	v0 S	Claude Code S
Tagline	Google Docs with an AI collaborator baked in.	One API, every model. Pay-as-you-go, no subscriptions.	Vercel's AI-powered UI generator. Prompt to shadcn component.	Anthropic's CLI agent. Opus-powered, operates on your repo directly.
Category	Writing	Dev Platform	Design	Coding
Pricing	Free + $12/mo	Pay per token — model-dependent	Free + $20/mo	Part of Claude Pro/Max/Team plans
Best for	Essays, long-form drafts, thinking on the page.	Developers experimenting across models. Apps that want fallback logic.	Frontend devs, PMs prototyping UIs, anyone on Next.js.	Developers who want an agent, not autocomplete. Large refactors, tests, docs.
Strengths	Clean writing UX — distraction-free +++ prompt triggers AI help Collaboration + AI feedback together	300+ models from one endpoint Automatic fallbacks between providers No subscription — just pay what you use	Ships working React + Tailwind code Shadcn/ui native One-click deploy to Vercel	Runs locally, edits your actual files Strong on large codebases with 1M context Great at multi-step tasks
Weaknesses	Less feature-rich than Google Docs AI ceiling below dedicated tools	Slight markup over direct API Some provider features not exposed	Best for shadcn stack Iterating can be fiddly	Terminal-based — learning curve Can't be used without Claude subscription
Kai's verdict	A-tier. Beautiful UX. The writing app I'd pick if I only wrote long-form.	S-tier for model-shopping. I use this for every prototype before committing.	S-tier. If you're on Vercel/shadcn, this is cheating.	S-tier if you live in the terminal. Different shape than Cursor — complementary, not replacement.
Link	Open →	Open →	Open →	Open →