{"slug": "opencode-zen", "name": "OpenCode Zen", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 4, "commenters": 6, "warners": 0, "score": 4.219, "rising": 1.35, "first": "2026-03-24", "latest": "2026-09-16", "why": "I'd rather just use cheap tokens from OpenCode Zen and Go.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 2, "compare": 0, "warn": 1}, "spark": [0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 1, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I'd rather just use cheap tokens from OpenCode Zen and Go.", "icon": true, "domain": "opencode.ai", "github_repo": null, "official_url": "https://opencode.ai/zen", "pricing": "", "aliases": ["OpenCode Zen"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 795681442, "item_id": 49730090, "url": "https://news.ycombinator.com/item?id=49730090", "by": "bellowsgulch", "date": "2026-09-16", "stance": "recommend", "quote": "I'd rather just use cheap tokens from OpenCode Zen and Go.", "excerpt": "I so wanted to be able to use Qwen3.8-27B locally on my fully loaded M1 Max 64GB when spider-mario recommended I use MTPLX[1], but I still found the general MLX MTP acceleration to be so poor, I'd rather just use cheap tokens from OpenCode Zen and Go. It's just too slow of a model. I know, I know there's new hardware, but my business paid like 4-5 grand for this MBP at the time, and I just don't feel the need to pay ", "context": "", "use_case": "cheap model tokens", "switched_from": "", "story": "Show HN: Swift-Qwen3.8-27B, -58.3% thinking, x1.95 speed, accuracy of xhigh"}, {"id": 787523330, "item_id": 49220208, "url": "https://news.ycombinator.com/item?id=49220208", "by": "saturn5k", "date": "2026-08-08", "stance": "recommend", "quote": "using V4 Flash Free with Hermes through Opencode Zen both personally and at my company and I've been having a great experience", "excerpt": "For the last 3 months I've been using V4 Flash Free with Hermes through Opencode Zen both personally and at my company and I've been having a great experience so far. It's my go-to model for terminal work, managing my entire ubuntu server, Cloudpanel, managing static websites, doing SEO audits, network tests, DNS troubleshooting, e-mail deliverability troubleshooting... Furthermore, in my company we are using MCPs fo", "context": "", "use_case": "model access", "switched_from": "", "story": "DeepSeek V4 Flash 0731"}, {"id": 763233520, "item_id": 47702095, "url": "https://news.ycombinator.com/item?id=47702095", "by": "delduca", "date": "2026-04-09", "stance": "recommend", "quote": "I switched to OpenCode Zen + GitHub Copilot.", "excerpt": "I also dropped Claude Code Max. I switched to OpenCode Zen + GitHub Copilot. For some reason, Claude Code burns through my quota really quickly. https://opencode.ai/zen", "context": "", "use_case": "AI coding", "switched_from": "Claude Code", "story": "Reallocating $100/Month Claude Code Spend to Zed and OpenRouter"}, {"id": 760098881, "item_id": 47506180, "url": "https://news.ycombinator.com/item?id=47506180", "by": "msh", "date": "2026-03-24", "stance": "recommend", "quote": "opencode zen (10usd) with Kimi k2.5 for the rest", "excerpt": "I would keep Claude code for the heavy lifting and then opencode zen (10usd) with Kimi k2.5 for the rest.", "context": "", "use_case": "lighter coding tasks", "switched_from": "", "story": "Ask HN: $50 monthly budget, which coding models would you recommend now?"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 790232240, "item_id": 49389515, "url": "https://news.ycombinator.com/item?id=49389515", "by": "bellowsgulch", "date": "2026-08-21", "stance": "warn", "quote": "I've been a bit disappointed with how they communicate to customers.", "excerpt": "I've been using OpenCode Zen and OpenCode Go for a while now, and I've been a bit disappointed with how they communicate to customers. There's no status page that I'm aware of, and at least with my private harness, connections frequently drop. Maybe OpenCode itself does this, too? Anyway, I suspect it was just pricing. They seemed to suggest they were running it on their own hardware? But I'm not sure that was actual", "context": "", "use_case": "model access", "switched_from": "", "story": "Ask HN: OpenCode no longer including DeepSeek?"}]}], "who": [], "tags": [], "use_cases": ["model access", "cheap model tokens", "model hosting", "free model access for agents", "ai coding", "lighter coding tasks"], "compared": [{"slug": "claude-code", "name": "Claude Code", "co": 2, "switched_from": 1, "switched_to": 0}, {"slug": "opencode", "name": "OpenCode", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "deepseek", "name": "DeepSeek", "co": 3, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49727511", "title": "Show HN: Swift-Qwen3.8-27B, -58.3% thinking, x1.95 speed, accuracy of xhigh", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49388835", "title": "Ask HN: OpenCode no longer including DeepSeek?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49214008", "title": "DeepSeek V4 Flash 0731", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48877371", "title": "What xAI's Grok Build CLI Actually Sends to xAI", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48241172", "title": "Models.dev: open-source database of AI model specs, pricing, and capabilities", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47700972", "title": "Reallocating $100/Month Claude Code Spend to Zed and OpenRouter", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {"recommend": 1}, "2026-04": {"recommend": 1}, "2026-05": {"neutral": 1}, "2026-06": {}, "2026-07": {"neutral": 1}, "2026-08": {"recommend": 1, "warn": 1}, "2026-09": {"recommend": 1}, "2026-10": {}}, "quotes": [{"id": 795681442, "item_id": 49730090, "url": "https://news.ycombinator.com/item?id=49730090", "by": "bellowsgulch", "date": "2026-09-16", "stance": "recommend", "quote": "I'd rather just use cheap tokens from OpenCode Zen and Go.", "excerpt": "I so wanted to be able to use Qwen3.8-27B locally on my fully loaded M1 Max 64GB when spider-mario recommended I use MTPLX[1], but I still found the general MLX MTP acceleration to be so poor, I'd rather just use cheap tokens from OpenCode Zen and Go. It's just too slow of a model. I know, I know there's new hardware, but my business paid like 4-5 grand for this MBP at the time, and I just don't feel the need to pay ", "context": "", "use_case": "cheap model tokens", "switched_from": "", "story": "Show HN: Swift-Qwen3.8-27B, -58.3% thinking, x1.95 speed, accuracy of xhigh"}, {"id": 790232240, "item_id": 49389515, "url": "https://news.ycombinator.com/item?id=49389515", "by": "bellowsgulch", "date": "2026-08-21", "stance": "warn", "quote": "I've been a bit disappointed with how they communicate to customers.", "excerpt": "I've been using OpenCode Zen and OpenCode Go for a while now, and I've been a bit disappointed with how they communicate to customers. There's no status page that I'm aware of, and at least with my private harness, connections frequently drop. Maybe OpenCode itself does this, too? Anyway, I suspect it was just pricing. They seemed to suggest they were running it on their own hardware? But I'm not sure that was actual", "context": "", "use_case": "model access", "switched_from": "", "story": "Ask HN: OpenCode no longer including DeepSeek?"}, {"id": 787523330, "item_id": 49220208, "url": "https://news.ycombinator.com/item?id=49220208", "by": "saturn5k", "date": "2026-08-08", "stance": "recommend", "quote": "using V4 Flash Free with Hermes through Opencode Zen both personally and at my company and I've been having a great experience", "excerpt": "For the last 3 months I've been using V4 Flash Free with Hermes through Opencode Zen both personally and at my company and I've been having a great experience so far. It's my go-to model for terminal work, managing my entire ubuntu server, Cloudpanel, managing static websites, doing SEO audits, network tests, DNS troubleshooting, e-mail deliverability troubleshooting... Furthermore, in my company we are using MCPs fo", "context": "", "use_case": "model access", "switched_from": "", "story": "DeepSeek V4 Flash 0731"}, {"id": 782099698, "item_id": 48881231, "url": "https://news.ycombinator.com/item?id=48881231", "by": "rpdillon", "date": "2026-07-12", "stance": "neutral", "quote": "US-hosted versions. Opencode Zen.", "excerpt": "I use omp with Deepseek v4 Flash and Pro. Probably put about 20 million tokens through it. I've never seen this. US-hosted versions. Opencode Zen.", "context": "", "use_case": "model hosting", "switched_from": "", "story": "What xAI's Grok Build CLI Actually Sends to xAI"}, {"id": 771865184, "item_id": 48241574, "url": "https://news.ycombinator.com/item?id=48241574", "by": "Imustaskforhelp", "date": "2026-05-22", "stance": "neutral", "quote": "I use opencode-zen from free version mostly if I want agents", "excerpt": "This seems really interesting, thanks maxloh for sharing. I have a quick question but https://aihubmix.com/model/coding-glm-5.1-free seems to be free in the chances of \"coding-glm-5.1-free is the open and free version of coding-glm-5.1. To ensure stable service performance, usage limits are in place: up to 5 requests per minute, 500 requests per day, and a daily token allowance of 1 million.\" Is there any catch aside", "context": "", "use_case": "free model access for agents", "switched_from": "", "story": "Models.dev: open-source database of AI model specs, pricing, and capabilities"}, {"id": 763233520, "item_id": 47702095, "url": "https://news.ycombinator.com/item?id=47702095", "by": "delduca", "date": "2026-04-09", "stance": "recommend", "quote": "I switched to OpenCode Zen + GitHub Copilot.", "excerpt": "I also dropped Claude Code Max. I switched to OpenCode Zen + GitHub Copilot. For some reason, Claude Code burns through my quota really quickly. https://opencode.ai/zen", "context": "", "use_case": "AI coding", "switched_from": "Claude Code", "story": "Reallocating $100/Month Claude Code Spend to Zed and OpenRouter"}, {"id": 760098881, "item_id": 47506180, "url": "https://news.ycombinator.com/item?id=47506180", "by": "msh", "date": "2026-03-24", "stance": "recommend", "quote": "opencode zen (10usd) with Kimi k2.5 for the rest", "excerpt": "I would keep Claude code for the heavy lifting and then opencode zen (10usd) with Kimi k2.5 for the rest.", "context": "", "use_case": "lighter coding tasks", "switched_from": "", "story": "Ask HN: $50 monthly budget, which coding models would you recommend now?"}]}