{"slug": "glm-coding-plan", "name": "GLM Coding Plan", "category": "ai-coding", "category_name": "AI coding tools", "description": "", "recommenders": 5, "commenters": 9, "warners": 1, "score": 4.341, "rising": -0.31, "first": "2026-01-15", "latest": "2026-09-23", "why": "Genuine advice: supplement your Claude Code plan with a GLM Coding plan", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 5, "neutral": 2, "compare": 1, "warn": 1}, "spark": [0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 1, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "Genuine advice: supplement your Claude Code plan with a GLM Coding plan", "kind": "", "icon": false, "domain": "z.ai", "github_repo": null, "official_url": "https://z.ai/subscribe", "pricing": "", "aliases": ["GLM Coding Plan", "GLM Coding plan"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 780906114, "item_id": 48806632, "url": "https://news.ycombinator.com/item?id=48806632", "by": "tasuki", "date": "2026-07-06", "version": null, "stance": "recommend", "quote": "am ready to jump ship to OpenCode Go or GLM Coding Plan", "excerpt": "FYI the name is Mario Zechner[0]. I'm also grumpy and old and also use Pi for the same reasons as you. I also use an OpenAI subscription (the models aren't entirely bad), but am ready to jump ship to OpenCode Go or GLM Coding Plan any minute. And I've been watching the Claude Code shitshow with glee! [0]: https://mariozechner.at/", "context": "", "use_case": "", "switched_from": "", "story": "Anthropic's Method to Losing Goodwill in a Few Easy Steps"}, {"id": 765698400, "item_id": 47856150, "url": "https://news.ycombinator.com/item?id=47856150", "by": "2001zhaozhao", "date": "2026-04-21", "version": null, "stance": "recommend", "quote": "That's what GLM coding plan is doing and it works fine for them.", "excerpt": "Apparently it's just an A/B test. Legit LMAO moment, speedrunning reputation destruction to your entire userbase just to test a question whose answer you can probably already guess. --- > For clarity, we're running a small test on ~2% of new prosumer signups. Existing Pro and Max subscribers aren't affected. > When we launched Max a year ago, it didn't include Claude Code, Cowork didn't exist, and agents that run for", "context": "", "use_case": "", "switched_from": "", "story": "Claude Code removed from Anthropic's Pro plan"}, {"id": 760590848, "item_id": 47536928, "url": "https://news.ycombinator.com/item?id=47536928", "by": "HDBaseT", "date": "2026-03-26", "version": null, "stance": "recommend", "quote": "you can edit you .env (~/.claude/settings.json) with an API key from the GLM Settings page", "excerpt": "You can! According to the GLM documentation at least, you can edit you .env (~/.claude/settings.json) with an API key from the GLM Settings page. [0]. { \"env\": { \"ANTHROPIC_AUTH_TOKEN\": \"your_zai_api_key\", \"ANTHROPIC_BASE_URL\": \"https://api.z.ai/api/anthropic\", \"API_TIMEOUT_MS\": \"3000000\" } } Whilst you need to generate an API Key, you are still using the 'GLM Coding Plan' as per 'Methods for Using the GLM Coding Pla", "context": "", "use_case": "Model access for Claude Code", "switched_from": "", "story": "Anthropic Update on Session Limits"}, {"id": 746262688, "item_id": 46641418, "url": "https://news.ycombinator.com/item?id=46641418", "by": "bigyabai", "date": "2026-01-15", "version": null, "stance": "recommend", "quote": "Genuine advice: supplement your Claude Code plan with a GLM Coding plan", "excerpt": "Genuine advice: supplement your Claude Code plan with a GLM Coding plan: https://z.ai/subscribe GLM 4.7 is not a \"Sonnet killer\" but it will work just as well for sketching out easier projects, web design and terminal usage. After a while I cancelled my Claude Code plan because I simply didn't do anything that GLM couldn't hammer out equally as well.", "context": "", "use_case": "Cheaper coding model plan", "switched_from": "Claude Code", "story": "Claude Cowork Runs Linux VM via Apple Virtualization Framework"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 772763937, "item_id": 48297746, "url": "https://news.ycombinator.com/item?id=48297746", "by": "BeetleB", "date": "2026-05-27", "version": null, "stance": "warn", "quote": "I won't even renew my annual Z.ai plan - it's become too expensive", "excerpt": "I use GLM-5.1. It's good enough for personal stuff. It doesn't compare to the latest Opus I use at work. You can certainly argue I don't need Opus for work, but there is clearly a difference. Also, at least with z.ai, GLM-5.1 is s l o w! After using Claude at work, I get really impatient with GLM-5.1 at home. When doing \"true\" vibe coding (i.e. not really examining the code), Opus is a ton faster (easily 5x). But yea", "context": "", "use_case": "", "switched_from": "", "story": "I think Anthropic and OpenAI have found product-market fit"}]}], "who": [{"by": "shelled", "context": "new to agentic coding, 2-3 months", "url": "https://news.ycombinator.com/item?id=49812308", "date": "2026-09-23"}], "tags": [], "use_cases": ["coding", "ai coding subscription", "model access for claude code", "cheaper coding model plan"], "compared": [{"slug": "claude-code", "name": "Claude Code", "co": 2, "switched_from": 1, "switched_to": 0}, {"slug": "claude-opus", "name": "Claude Opus", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "glm", "name": "GLM", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49803892", "title": "Claude Opus 5.5", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49737922", "title": "How GLM built its own inference infrastructure", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48837877", "title": "Rewriting Bun in Rust", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48821102", "title": "\"We're extending access to Claude Fable 5 on all paid plans through July 12.\"", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48803751", "title": "Anthropic's Method to Losing Goodwill in a Few Easy Steps", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48751752", "title": "ZCode: Claude Code from the Makers of GLM", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {"recommend": 1}, "2026-02": {}, "2026-03": {"recommend": 1}, "2026-04": {"recommend": 1}, "2026-05": {"warn": 1}, "2026-06": {}, "2026-07": {"neutral": 1, "recommend": 1, "compare": 1}, "2026-08": {}, "2026-09": {"recommend": 1, "neutral": 1}, "2026-10": {}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 796996928, "item_id": 49812308, "url": "https://news.ycombinator.com/item?id=49812308", "by": "shelled", "date": "2026-09-23", "version": null, "stance": "neutral", "quote": "I am on a GLM Coding plan subscription (old price; their base coding plan) right now", "excerpt": "Hey. I am on a GLM Coding plan subscription (old price; their base coding plan) right now and share the key (this will go away soon). I was thinking of going with a subscription of Claude or Codex. The reason (at least that's what I am assuming): with OpenRouter or any PAYG per token setup there will be the anxiety of using up all the tokens in days or maybe 1-2 weeks instead of a month (say I set myself a budget of ", "context": "new to agentic coding, 2-3 months", "use_case": "coding", "switched_from": "", "story": "Claude Opus 5.5"}, {"id": 795819280, "item_id": 49738705, "url": "https://news.ycombinator.com/item?id=49738705", "by": "asp_hornet", "date": "2026-09-17", "version": null, "stance": "recommend", "quote": "", "excerpt": "The way I look at it, their coding plan doesn\u2019t retain data or use it for training making it one of the cheaper plans for me. https://docs.z.ai/legal-agreement/privacy-policy", "context": "", "use_case": "AI coding subscription", "switched_from": "", "story": "How GLM built its own inference infrastructure"}, {"id": 781473602, "item_id": 48842100, "url": "https://news.ycombinator.com/item?id=48842100", "by": "KronisLV", "date": "2026-07-09", "version": null, "stance": "compare", "quote": "The GLM Coding Plan seems to have lower token limits than the corresponding Anthropic Max subscriptions", "excerpt": "I did some more sizeable work with GLM 5.2 on Max reasoning (planning and implementing 8 features end to end) and it performed pretty well, but worse than Opus 4.8, with largely the same adversarial agent review loop. Opus 4.8 still found some real issues afterwards and spent about an hour fixing things, before the code was good enough to ship. Overall promising, wrote about it here: https://blog.kronis.dev/blog/z-ai", "context": "", "use_case": "", "switched_from": "", "story": "Rewriting Bun in Rust"}, {"id": 781253409, "item_id": 48828338, "url": "https://news.ycombinator.com/item?id=48828338", "by": "KronisLV", "date": "2026-07-07", "version": null, "stance": "compare", "quote": "I also compared them against GLM Coding Plan", "excerpt": "Using Opus 4.8 on their Max 5x plan (108 EUR with VAT) would have cost me around 4600 EUR at API rates: https://news.ycombinator.com/item?id=48684539 I also compared them against GLM Coding Plan (cause everyone was positive of the model): https://blog.kronis.dev/blog/z-ai-s-glm-5-2-is-a-great-model-but-is-it-good-value/ and Anthropic still gives you a bit more tokens despite having some of the presumably most expensi", "context": "", "use_case": "", "switched_from": "", "story": "\"We're extending access to Claude Fable 5 on all paid plans through July 12.\""}, {"id": 780906114, "item_id": 48806632, "url": "https://news.ycombinator.com/item?id=48806632", "by": "tasuki", "date": "2026-07-06", "version": null, "stance": "recommend", "quote": "am ready to jump ship to OpenCode Go or GLM Coding Plan", "excerpt": "FYI the name is Mario Zechner[0]. I'm also grumpy and old and also use Pi for the same reasons as you. I also use an OpenAI subscription (the models aren't entirely bad), but am ready to jump ship to OpenCode Go or GLM Coding Plan any minute. And I've been watching the Claude Code shitshow with glee! [0]: https://mariozechner.at/", "context": "", "use_case": "", "switched_from": "", "story": "Anthropic's Method to Losing Goodwill in a Few Easy Steps"}, {"id": 780046321, "item_id": 48752895, "url": "https://news.ycombinator.com/item?id=48752895", "by": "qaz_plm", "date": "2026-07-01", "version": null, "stance": "neutral", "quote": "", "excerpt": "Peak hours are 14:00\u201318:00 (UTC+8) https://docs.z.ai/devpack/overview", "context": "", "use_case": "", "switched_from": "", "story": "ZCode: Claude Code from the Makers of GLM"}, {"id": 772763937, "item_id": 48297746, "url": "https://news.ycombinator.com/item?id=48297746", "by": "BeetleB", "date": "2026-05-27", "version": null, "stance": "warn", "quote": "I won't even renew my annual Z.ai plan - it's become too expensive", "excerpt": "I use GLM-5.1. It's good enough for personal stuff. It doesn't compare to the latest Opus I use at work. You can certainly argue I don't need Opus for work, but there is clearly a difference. Also, at least with z.ai, GLM-5.1 is s l o w! After using Claude at work, I get really impatient with GLM-5.1 at home. When doing \"true\" vibe coding (i.e. not really examining the code), Opus is a ton faster (easily 5x). But yea", "context": "", "use_case": "", "switched_from": "", "story": "I think Anthropic and OpenAI have found product-market fit"}, {"id": 765698400, "item_id": 47856150, "url": "https://news.ycombinator.com/item?id=47856150", "by": "2001zhaozhao", "date": "2026-04-21", "version": null, "stance": "recommend", "quote": "That's what GLM coding plan is doing and it works fine for them.", "excerpt": "Apparently it's just an A/B test. Legit LMAO moment, speedrunning reputation destruction to your entire userbase just to test a question whose answer you can probably already guess. --- > For clarity, we're running a small test on ~2% of new prosumer signups. Existing Pro and Max subscribers aren't affected. > When we launched Max a year ago, it didn't include Claude Code, Cowork didn't exist, and agents that run for", "context": "", "use_case": "", "switched_from": "", "story": "Claude Code removed from Anthropic's Pro plan"}, {"id": 760590848, "item_id": 47536928, "url": "https://news.ycombinator.com/item?id=47536928", "by": "HDBaseT", "date": "2026-03-26", "version": null, "stance": "recommend", "quote": "you can edit you .env (~/.claude/settings.json) with an API key from the GLM Settings page", "excerpt": "You can! According to the GLM documentation at least, you can edit you .env (~/.claude/settings.json) with an API key from the GLM Settings page. [0]. { \"env\": { \"ANTHROPIC_AUTH_TOKEN\": \"your_zai_api_key\", \"ANTHROPIC_BASE_URL\": \"https://api.z.ai/api/anthropic\", \"API_TIMEOUT_MS\": \"3000000\" } } Whilst you need to generate an API Key, you are still using the 'GLM Coding Plan' as per 'Methods for Using the GLM Coding Pla", "context": "", "use_case": "Model access for Claude Code", "switched_from": "", "story": "Anthropic Update on Session Limits"}, {"id": 746262688, "item_id": 46641418, "url": "https://news.ycombinator.com/item?id=46641418", "by": "bigyabai", "date": "2026-01-15", "version": null, "stance": "recommend", "quote": "Genuine advice: supplement your Claude Code plan with a GLM Coding plan", "excerpt": "Genuine advice: supplement your Claude Code plan with a GLM Coding plan: https://z.ai/subscribe GLM 4.7 is not a \"Sonnet killer\" but it will work just as well for sketching out easier projects, web design and terminal usage. After a while I cancelled my Claude Code plan because I simply didn't do anything that GLM couldn't hammer out equally as well.", "context": "", "use_case": "Cheaper coding model plan", "switched_from": "Claude Code", "story": "Claude Cowork Runs Linux VM via Apple Virtualization Framework"}]}