{"slug": "synthetic", "name": "Synthetic", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 3, "commenters": 7, "warners": 0, "score": 3.558, "rising": -0.98, "first": "2025-11-08", "latest": "2026-07-19", "why": "https://synthetic.new with Kimi K2.5 works surprisingly well for small tasks where I still make all the decisions.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 4, "compare": 0, "warn": 0}, "spark": [1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "https://synthetic.new with Kimi K2.5 works surprisingly well for small tasks where I still make all the decisions.", "icon": true, "domain": "synthetic.new", "github_repo": null, "official_url": "https://synthetic.new", "pricing": "", "aliases": ["Synthetic", "Synthetic.new", "synthetic.new"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 762165425, "item_id": 47635339, "url": "https://news.ycombinator.com/item?id=47635339", "by": "acheong08", "date": "2026-04-03", "stance": "recommend", "quote": "https://synthetic.new with Kimi K2.5 works surprisingly well for small tasks where I still make all the decisions.", "excerpt": "I get GitHub Copilot Pro for free for some reason. One day I checked and it was just there. So I use that until it runs out. When it does, https://synthetic.new with Kimi K2.5 works surprisingly well for small tasks where I still make all the decisions. But I find no matter what I use, it still makes more sense to code by hand for anything that actually matters. The things I've vibe coded are throwaway scripts to gen", "context": "", "use_case": "small coding tasks", "switched_from": "", "story": "Ask HN: What are you moving on to now that Claude Code is so rate limited?"}, {"id": 741939426, "item_id": 46371214, "url": "https://news.ycombinator.com/item?id=46371214", "by": "logicprog", "date": "2025-12-23", "stance": "recommend", "quote": "OpenCode + CodeNomad GUI + Synthetic.new subscription (Kimi K2 Thinking model mostly)", "excerpt": "OpenCode + CodeNomad GUI + Synthetic.new subscription (Kimi K2 Thinking model mostly)", "context": "", "use_case": "model access subscription", "switched_from": "", "story": "Ask HN: What's your current agentic coding setup?"}, {"id": 733714086, "item_id": 45857130, "url": "https://news.ycombinator.com/item?id=45857130", "by": "sheepscreek", "date": "2025-11-08", "stance": "recommend", "quote": "I am also evaluating Synthetic's (synthetic.new) open-source model inference subscription and I like it a lot.", "excerpt": "I used their $50 plan and with the previously offered Qwen3 coder 480B. While fast - none of the \u201csupported\u201d tools I tried were able to use it in a way that didn\u2019t hit the per minute request limit in a few seconds. It was incredibly frustrating. For the record, I tried OpenCoder, VSCode, Quen Coder CLI, octofriend and a few others I don\u2019t remember. Fast forward to now, when GLM 4.6 has replaced Qwen3 coder in their s", "context": "", "use_case": "open-source model inference", "switched_from": "", "story": "Cerebras Code now supports GLM 4.6 at 1000 tokens/sec"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["model inference hosting", "llm provider for coding", "open-source model subscription", "small coding tasks", "model access subscription", "ai model subscription backup"], "compared": [{"slug": "glm", "name": "GLM", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "opencode", "name": "OpenCode", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48969291", "title": "Moonshot AI suspends new subscriptions due to Kimi K3 demand", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48626866", "title": "GLM 5.2 vs. Opus", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47923357", "title": "GitHub Copilot is moving to usage-based billing", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47626833", "title": "Ask HN: What are you moving on to now that Claude Code is so rate limited?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46370768", "title": "Ask HN: What's your current agentic coding setup?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=45904551", "title": "GPT-5.1: A smarter, more conversational ChatGPT", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1, "neutral": 1}, "2025-12": {"recommend": 1}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {"recommend": 1, "neutral": 1}, "2026-05": {}, "2026-06": {"neutral": 1}, "2026-07": {"neutral": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 783537104, "item_id": 48971069, "url": "https://news.ycombinator.com/item?id=48971069", "by": "sroerick", "date": "2026-07-19", "stance": "neutral", "quote": "I have been using synthetic and my understanding is that they plan on hosting Kimi3.", "excerpt": "I have been using synthetic and my understanding is that they plan on hosting Kimi3. Open models mean Inferrence is distributed", "context": "", "use_case": "model inference hosting", "switched_from": "", "story": "Moonshot AI suspends new subscriptions due to Kimi K3 demand"}, {"id": 778159617, "item_id": 48634976, "url": "https://news.ycombinator.com/item?id=48634976", "by": "hmokiguess", "date": "2026-06-22", "stance": "neutral", "quote": "sounds like a good deal!", "excerpt": "how do I configure claude code / pi with it? sounds like a good deal! EDIT: I've RTFM lol, thanks for the links, will give it a shot!", "context": "", "use_case": "LLM provider for coding", "switched_from": "", "story": "GLM 5.2 vs. Opus"}, {"id": 767019571, "item_id": 47938723, "url": "https://news.ycombinator.com/item?id=47938723", "by": "arjun-mavonic", "date": "2026-04-28", "stance": "neutral", "quote": "I have switched from all big subscriptions and now have moved to many small subscriptions", "excerpt": "I knew they were burning money with those earlier limits. But thanks we had them a good price until we needed them. Now that GLM, Opencode Go, Crof AI, Synthetic.new, and many many more. They give these opensource source models. I have switched from all big subscriptions and now have moved to many small subscriptions and I am now trying see who gives best accuracy(quants), Speed (tokens/second) and Usage Limits at lo", "context": "", "use_case": "open-source model subscription", "switched_from": "", "story": "GitHub Copilot is moving to usage-based billing"}, {"id": 762165425, "item_id": 47635339, "url": "https://news.ycombinator.com/item?id=47635339", "by": "acheong08", "date": "2026-04-03", "stance": "recommend", "quote": "https://synthetic.new with Kimi K2.5 works surprisingly well for small tasks where I still make all the decisions.", "excerpt": "I get GitHub Copilot Pro for free for some reason. One day I checked and it was just there. So I use that until it runs out. When it does, https://synthetic.new with Kimi K2.5 works surprisingly well for small tasks where I still make all the decisions. But I find no matter what I use, it still makes more sense to code by hand for anything that actually matters. The things I've vibe coded are throwaway scripts to gen", "context": "", "use_case": "small coding tasks", "switched_from": "", "story": "Ask HN: What are you moving on to now that Claude Code is so rate limited?"}, {"id": 741939426, "item_id": 46371214, "url": "https://news.ycombinator.com/item?id=46371214", "by": "logicprog", "date": "2025-12-23", "stance": "recommend", "quote": "OpenCode + CodeNomad GUI + Synthetic.new subscription (Kimi K2 Thinking model mostly)", "excerpt": "OpenCode + CodeNomad GUI + Synthetic.new subscription (Kimi K2 Thinking model mostly)", "context": "", "use_case": "model access subscription", "switched_from": "", "story": "Ask HN: What's your current agentic coding setup?"}, {"id": 734634977, "item_id": 45914686, "url": "https://news.ycombinator.com/item?id=45914686", "by": "ojosilva", "date": "2025-11-13", "stance": "neutral", "quote": "I'm also a synthetic.new user, as a backup (and larger contexts)", "excerpt": "I'm also a synthetic.new user, as a backup (and larger contexts) for my Cerebras Coder subscription (zai-glm-4.6). I've been using the free Chatbox client [1] for like ~6 months and it works really well as a daily driver. I've tested the Romanian football player question with 3 different models (K2 Instruct, Deepseek Terminus, GLM 4.6) just now and they all went straight to my Brave MCP tool to query and replied all ", "context": "", "use_case": "AI model subscription backup", "switched_from": "", "story": "GPT-5.1: A smarter, more conversational ChatGPT"}, {"id": 733714086, "item_id": 45857130, "url": "https://news.ycombinator.com/item?id=45857130", "by": "sheepscreek", "date": "2025-11-08", "stance": "recommend", "quote": "I am also evaluating Synthetic's (synthetic.new) open-source model inference subscription and I like it a lot.", "excerpt": "I used their $50 plan and with the previously offered Qwen3 coder 480B. While fast - none of the \u201csupported\u201d tools I tried were able to use it in a way that didn\u2019t hit the per minute request limit in a few seconds. It was incredibly frustrating. For the record, I tried OpenCoder, VSCode, Quen Coder CLI, octofriend and a few others I don\u2019t remember. Fast forward to now, when GLM 4.6 has replaced Qwen3 coder in their s", "context": "", "use_case": "open-source model inference", "switched_from": "", "story": "Cerebras Code now supports GLM 4.6 at 1000 tokens/sec"}]}