{"slug": "hy", "name": "Hy", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 6, "commenters": 11, "warners": 0, "score": 6.297, "rising": -0.64, "first": "2026-03-16", "latest": "2026-10-06", "why": "Hy3 isn't as fast, but so far it seems to stay on track much more reliably than DS4 Flash.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 6, "neutral": 6, "compare": 0, "warn": 2}, "spark": [0, 0, 0, 0, 1, 0, 1, 0, 3, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "Hy3 isn't as fast, but so far it seems to stay on track much more reliably than DS4 Flash.", "kind": "", "icon": true, "domain": "openrouter.ai", "github_repo": null, "official_url": "https://openrouter.ai", "pricing": "", "aliases": ["Hy3", "Hy4", "hy3"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 791884000, "item_id": 49492750, "url": "https://news.ycombinator.com/item?id=49492750", "by": "minimaxir", "date": "2026-08-29", "stance": "recommend", "quote": "so Hy4 may be more compelling", "excerpt": "Hy4 apparently has ludicrous traction on OpenRouter already (https://openrouter.ai/tencent/hy4-preview), with trillions of tokens processed in a couple days: more than GLM 5.3 in a week. That said, it's relatively cheap with a 5% cache cost when everyone is still doing 10%/20% cache costs, so Hy4 may be more compelling.", "context": "", "use_case": "", "switched_from": "", "story": "Hy4 preview"}, {"id": 783005154, "item_id": 48937822, "url": "https://news.ycombinator.com/item?id=48937822", "by": "ignoramous", "date": "2026-07-16", "stance": "recommend", "quote": "are genuinely good enough as daily drivers, given the costs", "excerpt": "Possible, but pay-as-you-go Hy3 / DeepSeek v4 Pro / MiMo v2.5 Pro (from respective vendors) are genuinely good enough as daily drivers, given the costs (especially, low prices for input cache, which usually makes up 70%+ of total input for agentic workflows). I put in $10 in DeepSeek & Xiaomi MiMo, and I've barely used $1 each, in a week of coding work. Coding Plans by MiniMax ($20/mo for 1.7b tokens) and Z.ai (~$30/", "context": "", "use_case": "daily coding", "switched_from": "", "story": "Kimi K3 is now live"}, {"id": 781669648, "item_id": 48854353, "url": "https://news.ycombinator.com/item?id=48854353", "by": "nmfisher", "date": "2026-07-09", "stance": "recommend", "quote": "Hy3 isn't as fast, but so far it seems to stay on track much more reliably than DS4 Flash.", "excerpt": "I was playing with Hy3 via openrouter yesterday (and I've also been using DS4 Flash/Pro as a daily driver since I cancelled my Anthropic sub a week ago). I've found DS4 Flash to be very temperental (via Claude Code). The speed is great, but it often builds a completely wrong mental model and charges off down the wrong path. I find myself needing to rein it in regularly (and also compact the history, which undercuts t", "context": "", "use_case": "coding model", "switched_from": "", "story": "Hy3"}, {"id": 780879252, "item_id": 48804953, "url": "https://news.ycombinator.com/item?id=48804953", "by": "m_ke", "date": "2026-07-06", "stance": "recommend", "quote": "GLM 5.2, deepseek 4 Flash and the newly released Hy3 are Opus 4.8 and Sonnet 4.6 level models at a tiny fraction of the cost.", "excerpt": "https://openrouter.ai/models you can use these in hermes, cursor, openclaw, opencode, etc with 2 lines of config that claude code will happily do for you if you ask GLM 5.2, deepseek 4 Flash and the newly released Hy3 are Opus 4.8 and Sonnet 4.6 level models at a tiny fraction of the cost. I'm on the $200 claude plan and blew through my weekly limits with Fable in a day, then ended up wasting $20 with opus 4.8 overag", "context": "", "use_case": "", "switched_from": "", "story": "Anthropic's Method to Losing Goodwill in a Few Easy Steps"}, {"id": 773103616, "item_id": 48318976, "url": "https://news.ycombinator.com/item?id=48318976", "by": "simonw", "date": "2026-05-28", "stance": "recommend", "quote": "First model I've tried that gave me back HTML with a \"Change Pelican Color\" button", "excerpt": "First model I've tried that gave me back HTML with a \"Change Pelican Color\" button: https://static.simonwillison.net/static/2026/hy3-preview-pelican.html (Transcript: https://gist.github.com/simonw/c2a0d8ecd3056a2681319eae8fc3f7ce)", "context": "", "use_case": "", "switched_from": "", "story": "The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 781579440, "item_id": 48848715, "url": "https://news.ycombinator.com/item?id=48848715", "by": "minimaxir", "date": "2026-07-09", "stance": "warn", "quote": "I don't see a reason where you would use this model over competitors.", "excerpt": "A month ago I wrote a blog post about how Hy3 was topping the OpenRouter rankings despite no one talking about it: https://news.ycombinator.com/item?id=48317294 As of today, it has fallen to 8/9th on the rankings. I don't see a reason where you would use this model over competitors. However, price economics are bit confusing, as currently the effective input price of Hy3 via OpenRouter is now the same as DeepSeek-hos", "context": "", "use_case": "", "switched_from": "", "story": "Hy3"}, {"id": 773418096, "item_id": 48338631, "url": "https://news.ycombinator.com/item?id=48338631", "by": "minimaxir", "date": "2026-05-30", "stance": "warn", "quote": "Hy3 preview is no longer available as a free model. It has transitioned to a paid model.", "excerpt": "The first endpoint was closed. If you actually try and call it from the API you get this response: > Hy3 preview is no longer available as a free model. It has transitioned to a paid model. Continue using it here: https://openrouter.ai/tencent/hy3-preview The Kilo Code may have free traffic but if you check the numbers is still inconsequential relative to the trillions of tokens through OpenRouter.", "context": "", "use_case": "", "switched_from": "", "story": "The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin"}]}], "who": [{"by": "lloeki", "context": "Former i3 user, now sway user", "url": "https://news.ycombinator.com/item?id=47396466", "date": "2026-03-16"}], "tags": [], "use_cases": ["home use", "coding", "daily coding", "coding model", "ai model", "tiling layout plugin for hyprland"], "compared": [{"slug": "glm", "name": "GLM", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "openrouter", "name": "OpenRouter", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "deepseek-v4-flash", "name": "DeepSeek V4 Flash", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "mimo-pro", "name": "MiMo Pro", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "claude-opus", "name": "Claude Opus", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "deepseek-v4-pro", "name": "DeepSeek V4 Pro", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48847552", "title": "Hy3", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=48317294", "title": "The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=49492632", "title": "Hy4 preview", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49977979", "title": "Mistral Large 4", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49746618", "title": "Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48960218", "title": "The Kimi K3 Moment", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {"recommend": 1}, "2026-04": {}, "2026-05": {"neutral": 2, "recommend": 1, "warn": 1}, "2026-06": {}, "2026-07": {"recommend": 3, "warn": 1, "neutral": 1}, "2026-08": {"recommend": 1, "neutral": 1}, "2026-09": {"neutral": 1}, "2026-10": {"neutral": 1}}, "quotes": [{"id": 799665716, "item_id": 49979107, "url": "https://news.ycombinator.com/item?id=49979107", "by": "segmondy", "date": "2026-10-06", "stance": "neutral", "quote": "I use MiMov2.6Pro, DeepSeekv4.1Flash, GLM5.3, Hy4, Qwen3.8 and KimiK3 at home.", "excerpt": "I use Opus 5.5 at work. I use MiMov2.6Pro, DeepSeekv4.1Flash, GLM5.3, Hy4, Qwen3.8 and KimiK3 at home. Opus5.5 is not a game changer.", "context": "", "use_case": "home use", "switched_from": "", "story": "Mistral Large 4"}, {"id": 795975281, "item_id": 49748455, "url": "https://news.ycombinator.com/item?id=49748455", "by": "yowlingcat", "date": "2026-09-17", "stance": "neutral", "quote": "They did a Hy4 preview release", "excerpt": "That's correct. I think there can certainly be issues even with 4bpw with naive quantization (IE you'll notice far better results from a QAT 4bpw vs a naive 4bpw). One such method that I've been meaning to look into further is Tencent's AngelSlim QAT/PTQ approach. They did a Hy4 preview release thats an STQ_1_0 at 2.38 bpw: https://huggingface.co/AngelSlim/Hy4-preview-GGUF https://arxiv.org/abs/2602.21233 Of course, ", "context": "", "use_case": "", "switched_from": "", "story": "Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint"}, {"id": 791889152, "item_id": 49493072, "url": "https://news.ycombinator.com/item?id=49493072", "by": "vcryan", "date": "2026-08-29", "stance": "neutral", "quote": "I used Hy3 quite a bit for the type of tasks it was suited for.", "excerpt": "I used Hy3 quite a bit for the type of tasks it was suited for. Excited about this. My one concern over Hy3 was speed. In theory, it could be served much faster as a smaller model but it was relatively slow everywhere I could get it (including from Tencent directly) but also several other inference providers.", "context": "", "use_case": "", "switched_from": "", "story": "Hy4 preview"}, {"id": 791884000, "item_id": 49492750, "url": "https://news.ycombinator.com/item?id=49492750", "by": "minimaxir", "date": "2026-08-29", "stance": "recommend", "quote": "so Hy4 may be more compelling", "excerpt": "Hy4 apparently has ludicrous traction on OpenRouter already (https://openrouter.ai/tencent/hy4-preview), with trillions of tokens processed in a couple days: more than GLM 5.3 in a week. That said, it's relatively cheap with a 5% cache cost when everyone is still doing 10%/20% cache costs, so Hy4 may be more compelling.", "context": "", "use_case": "", "switched_from": "", "story": "Hy4 preview"}, {"id": 783407778, "item_id": 48962986, "url": "https://news.ycombinator.com/item?id=48962986", "by": "ignoramous", "date": "2026-07-18", "stance": "neutral", "quote": "I've begun experimenting with Hy3 (as an in-between Flash & Pro)", "excerpt": "> It's cheap enough to where I don't think about cost, made even cheaper by DeepSeek having the most effective and cheap caching in the industry I use DeepSeek v4 Flash & MiMo v2.5 Pro. Prefer the latter over DeepSeek v4 Pro because it costs the same while being equally good & less chattier for coding workloads. Although, I've begun experimenting with Hy3 (as an in-between Flash & Pro) & GLM 5.2 (for long-horizon tas", "context": "", "use_case": "coding", "switched_from": "", "story": "The Kimi K3 Moment"}, {"id": 783005154, "item_id": 48937822, "url": "https://news.ycombinator.com/item?id=48937822", "by": "ignoramous", "date": "2026-07-16", "stance": "recommend", "quote": "are genuinely good enough as daily drivers, given the costs", "excerpt": "Possible, but pay-as-you-go Hy3 / DeepSeek v4 Pro / MiMo v2.5 Pro (from respective vendors) are genuinely good enough as daily drivers, given the costs (especially, low prices for input cache, which usually makes up 70%+ of total input for agentic workflows). I put in $10 in DeepSeek & Xiaomi MiMo, and I've barely used $1 each, in a week of coding work. Coding Plans by MiniMax ($20/mo for 1.7b tokens) and Z.ai (~$30/", "context": "", "use_case": "daily coding", "switched_from": "", "story": "Kimi K3 is now live"}, {"id": 781669648, "item_id": 48854353, "url": "https://news.ycombinator.com/item?id=48854353", "by": "nmfisher", "date": "2026-07-09", "stance": "recommend", "quote": "Hy3 isn't as fast, but so far it seems to stay on track much more reliably than DS4 Flash.", "excerpt": "I was playing with Hy3 via openrouter yesterday (and I've also been using DS4 Flash/Pro as a daily driver since I cancelled my Anthropic sub a week ago). I've found DS4 Flash to be very temperental (via Claude Code). The speed is great, but it often builds a completely wrong mental model and charges off down the wrong path. I find myself needing to rein it in regularly (and also compact the history, which undercuts t", "context": "", "use_case": "coding model", "switched_from": "", "story": "Hy3"}, {"id": 781607888, "item_id": 48850493, "url": "https://news.ycombinator.com/item?id=48850493", "by": "andai", "date": "2026-07-09", "stance": "neutral", "quote": "Novita is offering free Hy3 on OpenRouter until July 21st", "excerpt": "Novita is offering free Hy3 on OpenRouter until July 21st https://openrouter.ai/tencent/hy3:free https://x.com/novita_labs/status/2074158304159510819", "context": "", "use_case": "AI model", "switched_from": "", "story": "Hy3"}, {"id": 781579440, "item_id": 48848715, "url": "https://news.ycombinator.com/item?id=48848715", "by": "minimaxir", "date": "2026-07-09", "stance": "warn", "quote": "I don't see a reason where you would use this model over competitors.", "excerpt": "A month ago I wrote a blog post about how Hy3 was topping the OpenRouter rankings despite no one talking about it: https://news.ycombinator.com/item?id=48317294 As of today, it has fallen to 8/9th on the rankings. I don't see a reason where you would use this model over competitors. However, price economics are bit confusing, as currently the effective input price of Hy3 via OpenRouter is now the same as DeepSeek-hos", "context": "", "use_case": "", "switched_from": "", "story": "Hy3"}, {"id": 780879252, "item_id": 48804953, "url": "https://news.ycombinator.com/item?id=48804953", "by": "m_ke", "date": "2026-07-06", "stance": "recommend", "quote": "GLM 5.2, deepseek 4 Flash and the newly released Hy3 are Opus 4.8 and Sonnet 4.6 level models at a tiny fraction of the cost.", "excerpt": "https://openrouter.ai/models you can use these in hermes, cursor, openclaw, opencode, etc with 2 lines of config that claude code will happily do for you if you ask GLM 5.2, deepseek 4 Flash and the newly released Hy3 are Opus 4.8 and Sonnet 4.6 level models at a tiny fraction of the cost. I'm on the $200 claude plan and blew through my weekly limits with Fable in a day, then ended up wasting $20 with opus 4.8 overag", "context": "", "use_case": "", "switched_from": "", "story": "Anthropic's Method to Losing Goodwill in a Few Easy Steps"}, {"id": 773418096, "item_id": 48338631, "url": "https://news.ycombinator.com/item?id=48338631", "by": "minimaxir", "date": "2026-05-30", "stance": "warn", "quote": "Hy3 preview is no longer available as a free model. It has transitioned to a paid model.", "excerpt": "The first endpoint was closed. If you actually try and call it from the API you get this response: > Hy3 preview is no longer available as a free model. It has transitioned to a paid model. Continue using it here: https://openrouter.ai/tencent/hy3-preview The Kilo Code may have free traffic but if you check the numbers is still inconsequential relative to the trillions of tokens through OpenRouter.", "context": "", "use_case": "", "switched_from": "", "story": "The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin"}, {"id": 773312608, "item_id": 48332038, "url": "https://news.ycombinator.com/item?id=48332038", "by": "segmondy", "date": "2026-05-29", "stance": "neutral", "quote": "The post is wrong, it's still free", "excerpt": "The post is wrong, it's still free, see - https://openrouter.ai/tencent/hy3-preview:free it's free in kilo.ai https://kilo.ai/models/tencent-hy3-preview-free It's free in a lot of places.", "context": "", "use_case": "", "switched_from": "", "story": "The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin"}, {"id": 773103616, "item_id": 48318976, "url": "https://news.ycombinator.com/item?id=48318976", "by": "simonw", "date": "2026-05-28", "stance": "recommend", "quote": "First model I've tried that gave me back HTML with a \"Change Pelican Color\" button", "excerpt": "First model I've tried that gave me back HTML with a \"Change Pelican Color\" button: https://static.simonwillison.net/static/2026/hy3-preview-pelican.html (Transcript: https://gist.github.com/simonw/c2a0d8ecd3056a2681319eae8fc3f7ce)", "context": "", "use_case": "", "switched_from": "", "story": "The mysterious Hy3 LLM is topping OpenRouter Model Rankings by a large margin"}, {"id": 771301536, "item_id": 48206346, "url": "https://news.ycombinator.com/item?id=48206346", "by": "stared", "date": "2026-05-20", "stance": "neutral", "quote": "vide Hy3 model, which this model claims to be 2.4T, while it is 295B", "excerpt": "I tried to run it, but estimate is 24\u201333T parameters, vide https://gist.github.com/stared/a86d7380937e6d0ab7920014866ace4c. It seems to be a huge overshot, vide Hy3 model, which this model claims to be 2.4T, while it is 295B.", "context": "", "use_case": "", "switched_from": "", "story": "Gemini 3.5 Flash"}, {"id": 758343456, "item_id": 47396466, "url": "https://news.ycombinator.com/item?id=47396466", "by": "lloeki", "date": "2026-03-16", "stance": "recommend", "quote": "hy3 is the only way I can bear using hyprland", "excerpt": "> tile windows to equal areas instead of BSP by default hy3? https://github.com/outfoxxed/hy3 (I'm an ex i3/now sway user and hy3 is the only way I can bear using hyprland)", "context": "Former i3 user, now sway user", "use_case": "Tiling layout plugin for Hyprland", "switched_from": "", "story": "Separating the Wayland Compositor and Window Manager"}]}