{"slug": "claude-pro-kagi-assistant-and-charm-hyper", "title": "Claude Pro, Kagi Assistant and Charm Hyper", "summary": "A user canceled their Claude Pro subscription, citing cost savings by switching to Kagi Assistant for general-purpose queries and Charm's Crush with Hyper for coding tasks, noting that Kagi Assistant often matches Claude's answers and that Hyper offers competitively priced LLMs. The user plans to use Anthropic tokens sparingly for Claude access via Crush or TypingMind.", "body_md": "# On Claude Pro, Kagi Assistant and Charm Hyper\n\n328 words, 2 minutes.\n\nI’ve cancelled my Claude Pro subscription. It wasn’t out of any dissatisfaction with Claude; on the contrary, I still think it’s the leading LLM for general use and especially for coding.\n\nNo, my choice was more because I realised I was wasting money.\n\nI already pay for [Kagi](https://kagi.com), and even upgraded to their Duo plan so I could\ngive my wife a search engine that works for her (versus the other way around).\nAs part of that subscription, I can use Kagi Assistant.\n\nFor general-purpose ‘consolidated search’ — answers — I ran tests of asking Claude and Kagi the same question, and more often than not they came out very similar, if not the same.\n\nI don’t do a lot of programming, but I probably end up running Claude Code once\na week to do something far faster than my rusty tech chops can muster. All of\nmy server machines run FreeBSD, which Claude Code recently [ended support for](https://github.com/anthropics/claude-code/issues/30640)\nwhen they moved to shipping their own package versus distribution via npm.\n\nI’ve been a fan of Charm’s mods for some time, which led me to their CLI coding\ntool, [Crush](https://github.com/charmbracelet/crush). Now Charm have extended Crush with a subscription inference\nservice called [Hyper](https://hyper.charm.land).\n\nCrush itself, being a Go-based binary, is considerably snappier to use than CC\nanyway, plus it’s entirely LLM-agnostic, simply needing API tokens. With Hyper,\none can now also access some very-keenly priced LLMs that are often almost as\ngood as Anthropic’s models. Although Hyper doesn’t yet support [Kimi K3](https://www.kimi.com/blog/kimi-k3),\nreleased this week and looking like a serious competitor to the leading\nfrontier models, you can bet it will soon (Charm are moving quickly with Crush\nand Hyper).\n\nSo I’m returning to buffering up some Anthropic tokens for when I really want\nto use Claude, either in Crush or for chat in [TypingMind](https://www.typingmind.com/). Otherwise, Kagi\nAssistant works really well.\n\nNot in the slightest bit important, but as an aide, Kagi’s logo doesn’t also\n[look like a butthole](https://velvetshark.com/ai-company-logos-that-look-like-buttholes).", "url": "https://wpnews.pro/news/claude-pro-kagi-assistant-and-charm-hyper", "canonical_source": "https://probably.co.uk/posts/claude-pro-kagi-assistant-charm-hyper/", "published_at": "2026-07-22 12:35:05+00:00", "updated_at": "2026-07-22 12:52:53.696950+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-tools", "ai-products"], "entities": ["Claude Pro", "Kagi", "Kagi Assistant", "Charm", "Crush", "Hyper", "Anthropic", "TypingMind"], "alternates": {"html": "https://wpnews.pro/news/claude-pro-kagi-assistant-and-charm-hyper", "markdown": "https://wpnews.pro/news/claude-pro-kagi-assistant-and-charm-hyper.md", "text": "https://wpnews.pro/news/claude-pro-kagi-assistant-and-charm-hyper.txt", "jsonld": "https://wpnews.pro/news/claude-pro-kagi-assistant-and-charm-hyper.jsonld"}}