{"slug": "k3", "name": "K3", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 3, "commenters": 3, "warners": 0, "score": 2.891, "rising": 1.67, "first": "2026-07-20", "latest": "2026-10-06", "why": "I've been happy experimenting with K3-medium as my default", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 0, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1], "listed": true, "loved": [], "caveat": "", "short_quote": "I've been happy experimenting with K3-medium as my default", "kind": "", "icon": false, "domain": null, "github_repo": null, "official_url": "", "pricing": "", "aliases": ["K3"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 799662128, "item_id": 49978883, "url": "https://news.ycombinator.com/item?id=49978883", "by": "rglover", "date": "2026-10-06", "stance": "recommend", "quote": "K3 has been my daily driver for a month or two now and it's dramatically reduced token spend", "excerpt": "Excited to try this. The low costs v. benchmarks alone here are worth a serious test. K3 has been my daily driver for a month or two now and it's dramatically reduced token spend (while not having much of a negative impact on productivity). This was the era of the AI race I was waiting for.", "context": "", "use_case": "daily AI use", "switched_from": "", "story": "Mistral Large 4"}, {"id": 794778897, "item_id": 49673681, "url": "https://news.ycombinator.com/item?id=49673681", "by": "conradludgate", "date": "2026-09-12", "stance": "recommend", "quote": "I've been happy experimenting with K3-medium as my default", "excerpt": "For personal use, Luna-xhigh on the Plus subscription. I only ever hit my limits if I decide to use Sol or Astra for a bit more quality. For work, given we pay API pricing anyway, I've been happy experimenting with K3-medium as my default, and now I'm planning on trying GLM 5.3 as well. Sol-medium is my fallback for my work purposes but I occasionally use Opus 4.8 as an additional reviewer. I like the open weight mod", "context": "does security hardening of own service", "use_case": "work coding", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 786836944, "item_id": 49177309, "url": "https://news.ycombinator.com/item?id=49177309", "by": "rglover", "date": "2026-08-04", "stance": "recommend", "quote": "First open model I haven't had the itch to leave on the shelf.", "excerpt": "FWIW, I switched to K3 last week and only went back (begrudgingly) to Opus when I hit a rate limit. First open model I haven't had the itch to leave on the shelf. It works as well as Opus 4.7/4.8 and in many cases (anecdotal, daily usage), I found it outperformed it.", "context": "", "use_case": "daily coding", "switched_from": "Opus", "story": "It's not a fear of \"AI communism\"; it's a fear of competitive market capitalism"}, {"id": 783747970, "item_id": 48984248, "url": "https://news.ycombinator.com/item?id=48984248", "by": "KronisLV", "date": "2026-07-20", "stance": "recommend", "quote": "the model is really, really good", "excerpt": "I wish they'd embed the Code UI as a tab, similar to Claude Code Desktop. There's really no real reason for those tools to be separate and for them not to give me something a bit nicer than just a TUI in the terminal. They already have a locally runnable web UI when you have Kimi (the CLI) installed: https://www.kimi.com/help/kimi-code/cli-getting-started kimi server run --foreground Though it's ever so slightly brok", "context": "", "use_case": "", "switched_from": "", "story": "Kimi Work"}]}], "caveats": [], "who": [{"by": "conradludgate", "context": "does security hardening of own service", "url": "https://news.ycombinator.com/item?id=49673681", "date": "2026-09-12"}], "tags": [], "use_cases": ["daily ai use", "work coding", "daily coding"], "compared": [{"slug": "claude-opus", "name": "Claude Opus", "co": 3, "switched_from": 1, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49977979", "title": "Mistral Large 4", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49672966", "title": "Ask HN: What default model do you use and why?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49169227", "title": "It's not a fear of \"AI communism\"; it's a fear of competitive market capitalism", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48981703", "title": "Kimi Work", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {"recommend": 1}, "2026-08": {"recommend": 1}, "2026-09": {"recommend": 1}, "2026-10": {"recommend": 1}}, "quotes": [{"id": 799662128, "item_id": 49978883, "url": "https://news.ycombinator.com/item?id=49978883", "by": "rglover", "date": "2026-10-06", "stance": "recommend", "quote": "K3 has been my daily driver for a month or two now and it's dramatically reduced token spend", "excerpt": "Excited to try this. The low costs v. benchmarks alone here are worth a serious test. K3 has been my daily driver for a month or two now and it's dramatically reduced token spend (while not having much of a negative impact on productivity). This was the era of the AI race I was waiting for.", "context": "", "use_case": "daily AI use", "switched_from": "", "story": "Mistral Large 4"}, {"id": 794778897, "item_id": 49673681, "url": "https://news.ycombinator.com/item?id=49673681", "by": "conradludgate", "date": "2026-09-12", "stance": "recommend", "quote": "I've been happy experimenting with K3-medium as my default", "excerpt": "For personal use, Luna-xhigh on the Plus subscription. I only ever hit my limits if I decide to use Sol or Astra for a bit more quality. For work, given we pay API pricing anyway, I've been happy experimenting with K3-medium as my default, and now I'm planning on trying GLM 5.3 as well. Sol-medium is my fallback for my work purposes but I occasionally use Opus 4.8 as an additional reviewer. I like the open weight mod", "context": "does security hardening of own service", "use_case": "work coding", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 786836944, "item_id": 49177309, "url": "https://news.ycombinator.com/item?id=49177309", "by": "rglover", "date": "2026-08-04", "stance": "recommend", "quote": "First open model I haven't had the itch to leave on the shelf.", "excerpt": "FWIW, I switched to K3 last week and only went back (begrudgingly) to Opus when I hit a rate limit. First open model I haven't had the itch to leave on the shelf. It works as well as Opus 4.7/4.8 and in many cases (anecdotal, daily usage), I found it outperformed it.", "context": "", "use_case": "daily coding", "switched_from": "Opus", "story": "It's not a fear of \"AI communism\"; it's a fear of competitive market capitalism"}, {"id": 783747970, "item_id": 48984248, "url": "https://news.ycombinator.com/item?id=48984248", "by": "KronisLV", "date": "2026-07-20", "stance": "recommend", "quote": "the model is really, really good", "excerpt": "I wish they'd embed the Code UI as a tab, similar to Claude Code Desktop. There's really no real reason for those tools to be separate and for them not to give me something a bit nicer than just a TUI in the terminal. They already have a locally runnable web UI when you have Kimi (the CLI) installed: https://www.kimi.com/help/kimi-code/cli-getting-started kimi server run --foreground Though it's ever so slightly brok", "context": "", "use_case": "", "switched_from": "", "story": "Kimi Work"}]}