What's new in
LumiChats.

We nearly doubled the AI model comparison library (435 → 903 side-by-side pages) with 13 in-demand models, gave comparison, glossary, feature and use-case links their own clean share-preview cards, fixed three pages that had no preview at all, broadened the blog's image variety, and made this changelog load smoothly as you scroll.

Claude Sonnet 5 is now available on LumiChats — Anthropic's newest and most agentic Sonnet, with near-Opus quality at Sonnet pricing — and you can pick it from the model menu today. We also published four new guides on the new model lineup, expanded the model-comparison library by 110 head-to-head pages (now 435 total), and refreshed the homepage to reflect the 45,000+ developers and students on the platform.

Every blog post now gets its own branded share image. When you or your readers share a LumiChats article on WhatsApp, X, LinkedIn, Slack, iMessage or anywhere else, the link unfurls into a clean, custom preview card built from that exact post — its headline, category and author — instead of a generic stock photo. The cards are generated automatically for every published article and every future one, at the exact size each platform expects, so shared links look professional and far more clickable.

Blog post pages are now significantly faster for users landing directly on an article. Five navigation paths that used to trigger full page reloads — logo, back to blog, next read, mobile sticky bar, and related posts — are all instant SPA transitions. Google Fonts inside the post page also moved from a render-blocking @import to a parallel <link> tag, cutting LCP time on first visit.

Blog font loading is now faster on every visit. DNS pre-resolution hints added for Google Fonts so browsers begin the lookup the moment the page starts parsing — improving font load times on older browsers and reducing layout shift on first paint.

Streaming responses are now visibly smoother and faster — especially in longer conversations. A focused performance overhaul of the chat engine eliminates the processing work that used to run on every single token, replacing it with a lightweight instant lookup. The result is a noticeably snappier feel as the AI types, with no stutter even at the end of a long session.

HTML rendering is now significantly more robust and visually richer. The renderer recovers cleanly from fenced output and pre-text prose that smaller models produce. Animations, animated counters, and progress bars are fully supported. The design system gains an extended accent palette, gradients, glow shadows, and animation tokens.

Site-wide legal and trust update — Privacy Policy, Terms of Service, Security page, and About page all updated in one pass. Governing law corrected to India. Stripe removed. Identity Protection added. About page now reflects 80+ countries and the LumiChats Offline #7 Product Hunt ranking.