{"slug": "chutes", "name": "Chutes", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 3, "commenters": 4, "warners": 0, "score": 2.989, "rising": -0.98, "first": "2025-11-25", "latest": "2026-07-16", "why": "They tell you exactly which model/quant and server config they use", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 1, "compare": 0, "warn": 0}, "spark": [1, 0, 0, 0, 0, 0, 2, 0, 1, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "They tell you exactly which model/quant and server config they use", "kind": "", "icon": true, "domain": "chutes.ai", "github_repo": null, "official_url": "https://chutes.ai", "pricing": "", "aliases": ["Chutes"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 783072864, "item_id": 48942054, "url": "https://news.ycombinator.com/item?id=48942054", "by": "ignoramous", "date": "2026-07-16", "stance": "recommend", "quote": "One can run open weights in an exclusive TEE'd GPU too", "excerpt": "> continuing to refuse to use chinese models due to security and IP concerns One can run open weights in an exclusive TEE'd GPU too, which still comes out cheaper than closed weight LLMs. Ex: https://chutes.ai/pricing", "context": "", "use_case": "Hosting open-weight models", "switched_from": "", "story": "Kimi K3 is now live"}, {"id": 769933152, "item_id": 48120822, "url": "https://news.ycombinator.com/item?id=48120822", "by": "irthomasthomas", "date": "2026-05-13", "stance": "recommend", "quote": "No its super easy.", "excerpt": "No its super easy. I think the confusion is due to the serving and hosting APIs that let you add your own GPUs to a pool and earn money. But for regular inference they have an openai responses API a basic chat app. You can signup to a $3 subscription, or deposit $5 and use your api key. https://chutes.ai/app/chute/2ff25e81-4586-5ec8-b892-3a6f342693d7 curl -X POST \\ https://llm.chutes.ai/v1/chat/completions \\ -H \"Auth", "context": "", "use_case": "AI model inference API", "switched_from": "", "story": "Best AI coding plan alternative to Claude and ChatGPT"}, {"id": 768064768, "item_id": 48004048, "url": "https://news.ycombinator.com/item?id=48004048", "by": "freakynit", "date": "2026-05-03", "stance": "recommend", "quote": "it seems to be quite successful", "excerpt": "We have chutes.ai for distributed GPU computing and it seems to be quite successful. https://chutes.ai/platform Tokens processed through OpenRouter gateway: https://openrouter.ai/provider/chutes", "context": "", "use_case": "distributed GPU compute", "switched_from": "", "story": "Ask HN: Why hasn't someone built a decentralized compute network?"}, {"id": 736798016, "item_id": 46049876, "url": "https://news.ycombinator.com/item?id=46049876", "by": "irthomasthomas", "date": "2025-11-25", "stance": "recommend", "quote": "They tell you exactly which model/quant and server config they use", "excerpt": "Yep, that was it! That really turned me off anthropic and closed models until they provide regular quality tests. I use chutes ai, now. They tell you exactly which model/quant and server config they use, so you know if you have trouble with a task, it's not the model.", "context": "", "use_case": "Hosted AI models", "switched_from": "", "story": "Claude Opus 4.5"}]}], "caveats": [], "who": [], "tags": [], "use_cases": ["hosting open-weight models", "ai model inference api", "distributed gpu compute", "hosted ai models"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48935342", "title": "Kimi K3 is now live", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48081266", "title": "Best AI coding plan alternative to Claude and ChatGPT", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47997262", "title": "Ask HN: Why hasn't someone built a decentralized compute network?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47834565", "title": "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46037637", "title": "Claude Opus 4.5", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {"neutral": 1}, "2026-05": {"recommend": 2}, "2026-06": {}, "2026-07": {"recommend": 1}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 783072864, "item_id": 48942054, "url": "https://news.ycombinator.com/item?id=48942054", "by": "ignoramous", "date": "2026-07-16", "stance": "recommend", "quote": "One can run open weights in an exclusive TEE'd GPU too", "excerpt": "> continuing to refuse to use chinese models due to security and IP concerns One can run open weights in an exclusive TEE'd GPU too, which still comes out cheaper than closed weight LLMs. Ex: https://chutes.ai/pricing", "context": "", "use_case": "Hosting open-weight models", "switched_from": "", "story": "Kimi K3 is now live"}, {"id": 769933152, "item_id": 48120822, "url": "https://news.ycombinator.com/item?id=48120822", "by": "irthomasthomas", "date": "2026-05-13", "stance": "recommend", "quote": "No its super easy.", "excerpt": "No its super easy. I think the confusion is due to the serving and hosting APIs that let you add your own GPUs to a pool and earn money. But for regular inference they have an openai responses API a basic chat app. You can signup to a $3 subscription, or deposit $5 and use your api key. https://chutes.ai/app/chute/2ff25e81-4586-5ec8-b892-3a6f342693d7 curl -X POST \\ https://llm.chutes.ai/v1/chat/completions \\ -H \"Auth", "context": "", "use_case": "AI model inference API", "switched_from": "", "story": "Best AI coding plan alternative to Claude and ChatGPT"}, {"id": 768064768, "item_id": 48004048, "url": "https://news.ycombinator.com/item?id=48004048", "by": "freakynit", "date": "2026-05-03", "stance": "recommend", "quote": "it seems to be quite successful", "excerpt": "We have chutes.ai for distributed GPU computing and it seems to be quite successful. https://chutes.ai/platform Tokens processed through OpenRouter gateway: https://openrouter.ai/provider/chutes", "context": "", "use_case": "distributed GPU compute", "switched_from": "", "story": "Ask HN: Why hasn't someone built a decentralized compute network?"}, {"id": 765482082, "item_id": 47842630, "url": "https://news.ycombinator.com/item?id=47842630", "by": "0xbadcafebee", "date": "2026-04-20", "stance": "neutral", "quote": "Chutes", "excerpt": "OpenCode Go, BlackBox, Chutes. https://codeberg.org/mutablecc/calculate-ai-cost/src/branch/main/subscription_vs_api_comparison.csv", "context": "", "use_case": "", "switched_from": "", "story": "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"}, {"id": 736798016, "item_id": 46049876, "url": "https://news.ycombinator.com/item?id=46049876", "by": "irthomasthomas", "date": "2025-11-25", "stance": "recommend", "quote": "They tell you exactly which model/quant and server config they use", "excerpt": "Yep, that was it! That really turned me off anthropic and closed models until they provide regular quality tests. I use chutes ai, now. They tell you exactly which model/quant and server config they use, so you know if you have trouble with a task, it's not the model.", "context": "", "use_case": "Hosted AI models", "switched_from": "", "story": "Claude Opus 4.5"}]}