{"slug": "grok-code", "name": "Grok Code", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 6, "commenters": 9, "warners": 0, "score": 5.666, "rising": -1.96, "first": "2025-11-02", "latest": "2026-05-11", "why": "I've found it to be many times faster and cheaper than Claude 4.5 or GPT 5 Codex while still being quite capable.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 6, "neutral": 3, "compare": 0, "warn": 0}, "spark": [3, 1, 1, 0, 0, 1, 0, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I've found it to be many times faster and cheaper than Claude 4.5 or GPT 5 Codex while still being quite capable.", "kind": "", "icon": true, "domain": "openrouter.ai", "github_repo": null, "official_url": "https://x.ai", "pricing": "", "aliases": ["Grok Code Fast 1", "Grok Code", "Grok Code Fast"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 765748848, "item_id": 47859303, "url": "https://news.ycombinator.com/item?id=47859303", "by": "deanc", "date": "2026-04-21", "version": null, "stance": "recommend", "quote": "I used it exclusively when it was free in Cursor and have nothing bad to say about it.", "excerpt": "Have to call out that comment about grok code being sub par. I used it exclusively when it was free in Cursor and have nothing bad to say about it. And that was months ago. I imagine it\u2019s a lot better now.", "context": "", "use_case": "Coding model", "switched_from": "", "story": "SpaceX and Cursor partnership. Right to acquire Cursor later this year"}, {"id": 763190256, "item_id": 47699391, "url": "https://news.ycombinator.com/item?id=47699391", "by": "deanc", "date": "2026-04-08", "version": null, "stance": "recommend", "quote": "Grok code was my daily driver for months while it was free and it was fantastic", "excerpt": "Grok code was my daily driver for months while it was free and it was fantastic - it is certainly no worse than it was a few months ago. Unfortunately with LLMs everything is based off your use case, domain and the context you give it. I also use Grok daily for health questions as the other models are too afraid to give input on medical matters", "context": "", "use_case": "Daily coding driver", "switched_from": "", "story": "Muse Spark: Scaling Towards Personal Superintelligence"}, {"id": 744800945, "item_id": 46550059, "url": "https://news.ycombinator.com/item?id=46550059", "by": "brainless", "date": "2026-01-08", "version": null, "stance": "recommend", "quote": "I get more work done these days with GLM or Grok Code (using opencode)", "excerpt": "I know this will sound strange, but SOTA model companies will eventually allow subscription based usage through third-party tools. For any usage whatsoever. Models are pretty much democratized. I use Claude Code and opencode and I get more work done these days with GLM or Grok Code (using opencode). Z.ai (GLM) subscription is so worth it. Also, mixing models, small and large ones, is the way to go. Different models f", "context": "", "use_case": "coding", "switched_from": "", "story": "Anthropic bans use of API in OpenCode CLI tool"}, {"id": 738486000, "item_id": 46155375, "url": "https://news.ycombinator.com/item?id=46155375", "by": "joshuamcginnis", "date": "2025-12-04", "version": null, "stance": "recommend", "quote": "lots of people are using it - presumably because it performs well and provides value.", "excerpt": "According to https://openrouter.ai/rankings, lots of people are using it - presumably because it performs well and provides value.", "context": "", "use_case": "", "switched_from": "", "story": "State of AI: An Empirical 100T Token Study with OpenRouter"}, {"id": 733893808, "item_id": 45868363, "url": "https://news.ycombinator.com/item?id=45868363", "by": "bko", "date": "2025-11-09", "version": null, "stance": "recommend", "quote": "I realized that it makes a huge difference.", "excerpt": "I thought the number of tokens per second doesn't matter until I used Grok Code Fast. I realized that it makes a huge difference. If it take more than 30s to run, I lose focus, and look at something else. I end up being a lot less productive. It also opens up the possibility to automate a lot more simple tasks. I would def recommend people try fast models", "context": "", "use_case": "Coding", "switched_from": "", "story": "Grok 4 Fast now has 2M context window"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["coding", "coding model", "daily coding driver", "coding tasks"], "compared": [{"slug": "openrouter", "name": "OpenRouter", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=45862833", "title": "Grok 4 Fast now has 2M context window", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=48092231", "title": "GitHub Copilot is deprecating Grok Code Fast 1", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47855293", "title": "SpaceX and Cursor partnership. Right to acquire Cursor later this year", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47692043", "title": "Muse Spark: Scaling Towards Personal Superintelligence", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46549823", "title": "Anthropic bans use of API in OpenCode CLI tool", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46154022", "title": "State of AI: An Empirical 100T Token Study with OpenRouter", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 3, "neutral": 2}, "2025-12": {"recommend": 1}, "2026-01": {"recommend": 1}, "2026-02": {}, "2026-03": {}, "2026-04": {"recommend": 1}, "2026-05": {"neutral": 1}, "2026-06": {}, "2026-07": {}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 769484816, "item_id": 48092801, "url": "https://news.ycombinator.com/item?id=48092801", "by": "Daedren", "date": "2026-05-11", "version": null, "stance": "neutral", "quote": "they're deprecating it because xAI is doing so upstream", "excerpt": "Keep in mind they're deprecating it because xAI is doing so upstream. https://docs.x.ai/developers/migration/may-15-retirement", "context": "", "use_case": "", "switched_from": "", "story": "GitHub Copilot is deprecating Grok Code Fast 1"}, {"id": 765748848, "item_id": 47859303, "url": "https://news.ycombinator.com/item?id=47859303", "by": "deanc", "date": "2026-04-21", "version": null, "stance": "recommend", "quote": "I used it exclusively when it was free in Cursor and have nothing bad to say about it.", "excerpt": "Have to call out that comment about grok code being sub par. I used it exclusively when it was free in Cursor and have nothing bad to say about it. And that was months ago. I imagine it\u2019s a lot better now.", "context": "", "use_case": "Coding model", "switched_from": "", "story": "SpaceX and Cursor partnership. Right to acquire Cursor later this year"}, {"id": 763190256, "item_id": 47699391, "url": "https://news.ycombinator.com/item?id=47699391", "by": "deanc", "date": "2026-04-08", "version": null, "stance": "recommend", "quote": "Grok code was my daily driver for months while it was free and it was fantastic", "excerpt": "Grok code was my daily driver for months while it was free and it was fantastic - it is certainly no worse than it was a few months ago. Unfortunately with LLMs everything is based off your use case, domain and the context you give it. I also use Grok daily for health questions as the other models are too afraid to give input on medical matters", "context": "", "use_case": "Daily coding driver", "switched_from": "", "story": "Muse Spark: Scaling Towards Personal Superintelligence"}, {"id": 744800945, "item_id": 46550059, "url": "https://news.ycombinator.com/item?id=46550059", "by": "brainless", "date": "2026-01-08", "version": null, "stance": "recommend", "quote": "I get more work done these days with GLM or Grok Code (using opencode)", "excerpt": "I know this will sound strange, but SOTA model companies will eventually allow subscription based usage through third-party tools. For any usage whatsoever. Models are pretty much democratized. I use Claude Code and opencode and I get more work done these days with GLM or Grok Code (using opencode). Z.ai (GLM) subscription is so worth it. Also, mixing models, small and large ones, is the way to go. Different models f", "context": "", "use_case": "coding", "switched_from": "", "story": "Anthropic bans use of API in OpenCode CLI tool"}, {"id": 738486000, "item_id": 46155375, "url": "https://news.ycombinator.com/item?id=46155375", "by": "joshuamcginnis", "date": "2025-12-04", "version": null, "stance": "recommend", "quote": "lots of people are using it - presumably because it performs well and provides value.", "excerpt": "According to https://openrouter.ai/rankings, lots of people are using it - presumably because it performs well and provides value.", "context": "", "use_case": "", "switched_from": "", "story": "State of AI: An Empirical 100T Token Study with OpenRouter"}, {"id": 735664672, "item_id": 45979042, "url": "https://news.ycombinator.com/item?id=45979042", "by": "segmenta", "date": "2025-11-19", "version": null, "stance": "neutral", "quote": "Will check out Grok Code Fast - thanks for the pointer.", "excerpt": "Will check out Grok Code Fast - thanks for the pointer. In my experience, coding agents can swing a lot in quality depending on the model\u2019s reasoning power. When the model starts making small but avoidable mistakes, the overhead tends to cancel out the benefit. Curious to see how Grok performs on multi-step coding tasks.", "context": "", "use_case": "", "switched_from": "", "story": "Show HN: RowboatX \u2013 open-source Claude Code for everyday automations"}, {"id": 733893808, "item_id": 45868363, "url": "https://news.ycombinator.com/item?id=45868363", "by": "bko", "date": "2025-11-09", "version": null, "stance": "recommend", "quote": "I realized that it makes a huge difference.", "excerpt": "I thought the number of tokens per second doesn't matter until I used Grok Code Fast. I realized that it makes a huge difference. If it take more than 30s to run, I lose focus, and look at something else. I end up being a lot less productive. It also opens up the possibility to automate a lot more simple tasks. I would def recommend people try fast models", "context": "", "use_case": "Coding", "switched_from": "", "story": "Grok 4 Fast now has 2M context window"}, {"id": 733825200, "item_id": 45864075, "url": "https://news.ycombinator.com/item?id=45864075", "by": "wqaatwt", "date": "2025-11-09", "version": null, "stance": "recommend", "quote": "", "excerpt": "Yet if you go to the actual model\u2019s page: https://openrouter.ai/x-ai/grok-code-fast-1 Cline and Kilo code are in the top 3. So how does that work? It\u2019s considerably cheaper than competing models like 2.5 flash, though. So its not that surprising", "context": "", "use_case": "", "switched_from": "", "story": "Grok 4 Fast now has 2M context window"}, {"id": 733810016, "item_id": 45863126, "url": "https://news.ycombinator.com/item?id=45863126", "by": "minimaxir", "date": "2025-11-08", "version": null, "stance": "neutral", "quote": "Grok Code Fast 1 is the most used model by a significant margin", "excerpt": "Going off OpenRouter's rankings (https://openrouter.ai/rankings), Grok Code Fast 1 is the most used model by a significant margin, and since those metrics are calculated as of this week, that's after providers stopped giving free promotional access to it. Grok 4 Fast is #5 on that list which was never free. In terms of models, Grok 4 Fast has essentially zero restrictions on safety, which a) makes it unusable for mos", "context": "", "use_case": "", "switched_from": "", "story": "Grok 4 Fast now has 2M context window"}, {"id": 732658384, "item_id": 45791149, "url": "https://news.ycombinator.com/item?id=45791149", "by": "tripplyons", "date": "2025-11-02", "version": null, "stance": "recommend", "quote": "I've found it to be many times faster and cheaper than Claude 4.5 or GPT 5 Codex while still being quite capable.", "excerpt": "Right now, I'm using Grok Code Fast 1 for coding tasks. I've found it to be many times faster and cheaper than Claude 4.5 or GPT 5 Codex while still being quite capable. The \"code-supernova-1-million\" stealth model was more capable, but it is unfortunately no longer available through any of providers. Hopefully it gets publicly released soon. My guess is that it is an updated code model from XAI/Grok. Having to switc", "context": "", "use_case": "coding tasks", "switched_from": "", "story": "Ask HN: Seriously, which AI coding thing is best?"}]}