{"slug": "groq", "name": "Groq", "category": "ai", "category_name": "AI models and assistants", "description": "Cloud AI inference platform serving open models on custom LPU hardware.", "recommenders": 6, "commenters": 7, "warners": 0, "score": 5.159, "rising": -1.96, "first": "2025-11-06", "latest": "2026-01-11", "why": "HN commenters use Groq for very fast, low-cost inference on open models like Llama 3, gpt-oss-20b and Whisper.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 6, "neutral": 1, "compare": 0, "warn": 0}, "spark": [1, 4, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0], "listed": true, "loved": ["Speed", "Model choice"], "caveat": "Policy changes", "short_quote": "I'm a fan, and I use Groq a lot for systems I build.", "icon": true, "domain": null, "github_repo": null, "official_url": "https://groq.com", "pricing": "freemium", "aliases": ["Groq"], "verdict": [{"text": "HN commenters use Groq for very fast, low-cost inference", "cites": [{"id": 742962720, "item_id": 46435170, "url": "https://news.ycombinator.com/item?id=46435170", "by": "ImPrajyoth", "date": "2025-12-30", "stance": "recommend", "quote": "With Groq speed (Llama 3 @ 800t/s)", "excerpt": "OP here. this is a cursed project lol, but i wanted to see: What happens if you replace the OS scheduler with an LLM? With Groq speed (Llama 3 @ 800t/s), inference is finally fast enough to be in the system loop. i built this TUI to monitor my process tree. instead of just showing CPU %, it checks the context (parent process, disk I/O) to decide if a process is compiling code or bloatware. It roasts, throttles, or ki", "context": "Built an LLM process monitor", "use_case": "fast LLM inference in scheduler", "switched_from": "", "story": "Show HN: Replacing my OS process scheduler with an LLM"}, {"id": 742139858, "item_id": 46383741, "url": "https://news.ycombinator.com/item?id=46383741", "by": "sgk284", "date": "2025-12-25", "stance": "recommend", "quote": "We use Groq with gpt-oss-20b, which gives great results and only adds ~250ms to the processing pipeline.", "excerpt": "Reranking is definitely the way to go. We personally found common reranker models to be a little too opaque (can't explain to the user why this result was picked) and not quite steerable enough, so we just use another LLM for reranking. We open-sourced our impl just this week: https://github.com/with-logic/intent We use Groq with gpt-oss-20b, which gives great results and only adds ~250ms to the processing pipeline. ", "context": "", "use_case": "LLM inference", "switched_from": "", "story": "Using Vectorize to build an unreasonably good search engine in 160 lines of code"}, {"id": 733371713, "item_id": 45835732, "url": "https://news.ycombinator.com/item?id=45835732", "by": "threeducks", "date": "2025-11-06", "stance": "recommend", "quote": "I used Groq (not to be confused with Grok), because it is free and very fast.", "excerpt": "While attempting to write my own script, I found that there are many websites which offer YouTube summaries, which are probably an easier solution. For example (not affiliated) https://www.easemate.ai/video-summary It even allows you to ask questions about the transcript. I also found a Python library for fetching YouTube video transcripts, but some issue mentioned that they got banned, so out of caution, I implement", "context": "", "use_case": "LLM API for summaries", "switched_from": "", "story": "I was right about dishwasher pods and now I can prove it [video]"}, {"id": 742493216, "item_id": 46405826, "url": "https://news.ycombinator.com/item?id=46405826", "by": "pjb88", "date": "2025-12-27", "stance": "recommend", "quote": "I'm a fan, and I use Groq a lot for systems I build.", "excerpt": "So... What will the actual impact on groq services be? I'm a fan, and I use Groq a lot for systems I build. I think they offer something different to most other providers (cheaper, faster, and until recently \"we don't store your data by default\") and it will be sad to see that fade.", "context": "builds systems using LLM APIs", "use_case": "LLM inference for built systems", "switched_from": "", "story": "Nvidia's $20B Antitrust Loophole (Not an Acquisition)"}, {"id": 740101490, "item_id": 46256343, "url": "https://news.ycombinator.com/item?id=46256343", "by": "hn_throw2025", "date": "2025-12-13", "stance": "recommend", "quote": "It's incredibly cheap and works reliably for me.", "excerpt": "I'm not the person you're replying to, but I use Whispering connected to the whisper-large-v3-turbo model on Groq. It's incredibly cheap and works reliably for me. I have got it to paste my voice transcriptions into Chrome (Gemini, Claude, ChatGPT) as well as Cursor. https://github.com/EpicenterHQ/epicenter", "context": "", "use_case": "hosting Whisper model inference", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}]}, {"text": " on open models like Llama 3, gpt-oss-20b and Whisper.", "cites": [{"id": 742962720, "item_id": 46435170, "url": "https://news.ycombinator.com/item?id=46435170", "by": "ImPrajyoth", "date": "2025-12-30", "stance": "recommend", "quote": "With Groq speed (Llama 3 @ 800t/s)", "excerpt": "OP here. this is a cursed project lol, but i wanted to see: What happens if you replace the OS scheduler with an LLM? With Groq speed (Llama 3 @ 800t/s), inference is finally fast enough to be in the system loop. i built this TUI to monitor my process tree. instead of just showing CPU %, it checks the context (parent process, disk I/O) to decide if a process is compiling code or bloatware. It roasts, throttles, or ki", "context": "Built an LLM process monitor", "use_case": "fast LLM inference in scheduler", "switched_from": "", "story": "Show HN: Replacing my OS process scheduler with an LLM"}, {"id": 742139858, "item_id": 46383741, "url": "https://news.ycombinator.com/item?id=46383741", "by": "sgk284", "date": "2025-12-25", "stance": "recommend", "quote": "We use Groq with gpt-oss-20b, which gives great results and only adds ~250ms to the processing pipeline.", "excerpt": "Reranking is definitely the way to go. We personally found common reranker models to be a little too opaque (can't explain to the user why this result was picked) and not quite steerable enough, so we just use another LLM for reranking. We open-sourced our impl just this week: https://github.com/with-logic/intent We use Groq with gpt-oss-20b, which gives great results and only adds ~250ms to the processing pipeline. ", "context": "", "use_case": "LLM inference", "switched_from": "", "story": "Using Vectorize to build an unreasonably good search engine in 160 lines of code"}, {"id": 740101490, "item_id": 46256343, "url": "https://news.ycombinator.com/item?id=46256343", "by": "hn_throw2025", "date": "2025-12-13", "stance": "recommend", "quote": "It's incredibly cheap and works reliably for me.", "excerpt": "I'm not the person you're replying to, but I use Whispering connected to the whisper-large-v3-turbo model on Groq. It's incredibly cheap and works reliably for me. I have got it to paste my voice transcriptions into Chrome (Gemini, Claude, ChatGPT) as well as Cursor. https://github.com/EpicenterHQ/epicenter", "context": "", "use_case": "hosting Whisper model inference", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}]}, {"text": " Complaints are rare; the one caveat raised is a worry that the service may change,", "cites": [{"id": 742493216, "item_id": 46405826, "url": "https://news.ycombinator.com/item?id=46405826", "by": "pjb88", "date": "2025-12-27", "stance": "recommend", "quote": "I'm a fan, and I use Groq a lot for systems I build.", "excerpt": "So... What will the actual impact on groq services be? I'm a fan, and I use Groq a lot for systems I build. I think they offer something different to most other providers (cheaper, faster, and until recently \"we don't store your data by default\") and it will be sad to see that fade.", "context": "builds systems using LLM APIs", "use_case": "LLM inference for built systems", "switched_from": "", "story": "Nvidia's $20B Antitrust Loophole (Not an Acquisition)"}]}, {"text": " since its policy of not storing data by default has recently ended.", "cites": [{"id": 742493216, "item_id": 46405826, "url": "https://news.ycombinator.com/item?id=46405826", "by": "pjb88", "date": "2025-12-27", "stance": "recommend", "quote": "I'm a fan, and I use Groq a lot for systems I build.", "excerpt": "So... What will the actual impact on groq services be? I'm a fan, and I use Groq a lot for systems I build. I think they offer something different to most other providers (cheaper, faster, and until recently \"we don't store your data by default\") and it will be sad to see that fade.", "context": "builds systems using LLM APIs", "use_case": "LLM inference for built systems", "switched_from": "", "story": "Nvidia's $20B Antitrust Loophole (Not an Acquisition)"}]}], "praise": [{"label": "Speed", "summary": "Inference is fast enough for latency-sensitive pipelines and even system loops.", "quotes": [{"id": 742962720, "item_id": 46435170, "url": "https://news.ycombinator.com/item?id=46435170", "by": "ImPrajyoth", "date": "2025-12-30", "stance": "recommend", "quote": "With Groq speed (Llama 3 @ 800t/s)", "excerpt": "OP here. this is a cursed project lol, but i wanted to see: What happens if you replace the OS scheduler with an LLM? With Groq speed (Llama 3 @ 800t/s), inference is finally fast enough to be in the system loop. i built this TUI to monitor my process tree. instead of just showing CPU %, it checks the context (parent process, disk I/O) to decide if a process is compiling code or bloatware. It roasts, throttles, or ki", "context": "Built an LLM process monitor", "use_case": "fast LLM inference in scheduler", "switched_from": "", "story": "Show HN: Replacing my OS process scheduler with an LLM"}, {"id": 742139858, "item_id": 46383741, "url": "https://news.ycombinator.com/item?id=46383741", "by": "sgk284", "date": "2025-12-25", "stance": "recommend", "quote": "We use Groq with gpt-oss-20b, which gives great results and only adds ~250ms to the processing pipeline.", "excerpt": "Reranking is definitely the way to go. We personally found common reranker models to be a little too opaque (can't explain to the user why this result was picked) and not quite steerable enough, so we just use another LLM for reranking. We open-sourced our impl just this week: https://github.com/with-logic/intent We use Groq with gpt-oss-20b, which gives great results and only adds ~250ms to the processing pipeline. ", "context": "", "use_case": "LLM inference", "switched_from": "", "story": "Using Vectorize to build an unreasonably good search engine in 160 lines of code"}, {"id": 733371713, "item_id": 45835732, "url": "https://news.ycombinator.com/item?id=45835732", "by": "threeducks", "date": "2025-11-06", "stance": "recommend", "quote": "I used Groq (not to be confused with Grok), because it is free and very fast.", "excerpt": "While attempting to write my own script, I found that there are many websites which offer YouTube summaries, which are probably an easier solution. For example (not affiliated) https://www.easemate.ai/video-summary It even allows you to ask questions about the transcript. I also found a Python library for fetching YouTube video transcripts, but some issue mentioned that they got banned, so out of caution, I implement", "context": "", "use_case": "LLM API for summaries", "switched_from": "", "story": "I was right about dishwasher pods and now I can prove it [video]"}]}, {"label": "Model choice", "summary": "Commenters run several open models on it, including Llama 3, gpt-oss-20b and whisper-large-v3-turbo.", "quotes": [{"id": 742962720, "item_id": 46435170, "url": "https://news.ycombinator.com/item?id=46435170", "by": "ImPrajyoth", "date": "2025-12-30", "stance": "recommend", "quote": "With Groq speed (Llama 3 @ 800t/s)", "excerpt": "OP here. this is a cursed project lol, but i wanted to see: What happens if you replace the OS scheduler with an LLM? With Groq speed (Llama 3 @ 800t/s), inference is finally fast enough to be in the system loop. i built this TUI to monitor my process tree. instead of just showing CPU %, it checks the context (parent process, disk I/O) to decide if a process is compiling code or bloatware. It roasts, throttles, or ki", "context": "Built an LLM process monitor", "use_case": "fast LLM inference in scheduler", "switched_from": "", "story": "Show HN: Replacing my OS process scheduler with an LLM"}, {"id": 742139858, "item_id": 46383741, "url": "https://news.ycombinator.com/item?id=46383741", "by": "sgk284", "date": "2025-12-25", "stance": "recommend", "quote": "We use Groq with gpt-oss-20b, which gives great results and only adds ~250ms to the processing pipeline.", "excerpt": "Reranking is definitely the way to go. We personally found common reranker models to be a little too opaque (can't explain to the user why this result was picked) and not quite steerable enough, so we just use another LLM for reranking. We open-sourced our impl just this week: https://github.com/with-logic/intent We use Groq with gpt-oss-20b, which gives great results and only adds ~250ms to the processing pipeline. ", "context": "", "use_case": "LLM inference", "switched_from": "", "story": "Using Vectorize to build an unreasonably good search engine in 160 lines of code"}, {"id": 740101490, "item_id": 46256343, "url": "https://news.ycombinator.com/item?id=46256343", "by": "hn_throw2025", "date": "2025-12-13", "stance": "recommend", "quote": "It's incredibly cheap and works reliably for me.", "excerpt": "I'm not the person you're replying to, but I use Whispering connected to the whisper-large-v3-turbo model on Groq. It's incredibly cheap and works reliably for me. I have got it to paste my voice transcriptions into Chrome (Gemini, Claude, ChatGPT) as well as Cursor. https://github.com/EpicenterHQ/epicenter", "context": "", "use_case": "hosting Whisper model inference", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}]}, {"label": "Low cost", "summary": "Described as cheap, and as free for one user's scripting use.", "quotes": [{"id": 740101490, "item_id": 46256343, "url": "https://news.ycombinator.com/item?id=46256343", "by": "hn_throw2025", "date": "2025-12-13", "stance": "recommend", "quote": "It's incredibly cheap and works reliably for me.", "excerpt": "I'm not the person you're replying to, but I use Whispering connected to the whisper-large-v3-turbo model on Groq. It's incredibly cheap and works reliably for me. I have got it to paste my voice transcriptions into Chrome (Gemini, Claude, ChatGPT) as well as Cursor. https://github.com/EpicenterHQ/epicenter", "context": "", "use_case": "hosting Whisper model inference", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}, {"id": 733371713, "item_id": 45835732, "url": "https://news.ycombinator.com/item?id=45835732", "by": "threeducks", "date": "2025-11-06", "stance": "recommend", "quote": "I used Groq (not to be confused with Grok), because it is free and very fast.", "excerpt": "While attempting to write my own script, I found that there are many websites which offer YouTube summaries, which are probably an easier solution. For example (not affiliated) https://www.easemate.ai/video-summary It even allows you to ask questions about the transcript. I also found a Python library for fetching YouTube video transcripts, but some issue mentioned that they got banned, so out of caution, I implement", "context": "", "use_case": "LLM API for summaries", "switched_from": "", "story": "I was right about dishwasher pods and now I can prove it [video]"}, {"id": 742493216, "item_id": 46405826, "url": "https://news.ycombinator.com/item?id=46405826", "by": "pjb88", "date": "2025-12-27", "stance": "recommend", "quote": "I'm a fan, and I use Groq a lot for systems I build.", "excerpt": "So... What will the actual impact on groq services be? I'm a fan, and I use Groq a lot for systems I build. I think they offer something different to most other providers (cheaper, faster, and until recently \"we don't store your data by default\") and it will be sad to see that fade.", "context": "builds systems using LLM APIs", "use_case": "LLM inference for built systems", "switched_from": "", "story": "Nvidia's $20B Antitrust Loophole (Not an Acquisition)"}]}, {"label": "Data privacy", "summary": "Suggested as an inference-only option for people worried about prompts being used for training.", "quotes": [{"id": 745191440, "item_id": 46574465, "url": "https://news.ycombinator.com/item?id=46574465", "by": "allie1", "date": "2026-01-11", "stance": "recommend", "quote": "you can use an inference only solution like Groq.", "excerpt": "They are so wildly used, and the companies usually tell you if they use your prompts for training. But again, at the current use case your code gets lost in the noise even if they do use it. Anthropic says they don\u2019t. Microsoft allows you to disable, same with ChatGPT. Unclear on Goole. But if you are worried, you can use an inference only solution like Groq.", "context": "", "use_case": "privacy-conscious LLM inference", "switched_from": "", "story": "Ask HN: Senior software engineers, how do you use Claude Code?"}, {"id": 742493216, "item_id": 46405826, "url": "https://news.ycombinator.com/item?id=46405826", "by": "pjb88", "date": "2025-12-27", "stance": "recommend", "quote": "I'm a fan, and I use Groq a lot for systems I build.", "excerpt": "So... What will the actual impact on groq services be? I'm a fan, and I use Groq a lot for systems I build. I think they offer something different to most other providers (cheaper, faster, and until recently \"we don't store your data by default\") and it will be sad to see that fade.", "context": "builds systems using LLM APIs", "use_case": "LLM inference for built systems", "switched_from": "", "story": "Nvidia's $20B Antitrust Loophole (Not an Acquisition)"}]}, {"label": "Reliability", "summary": "One user says it works reliably for voice transcription.", "quotes": [{"id": 740101490, "item_id": 46256343, "url": "https://news.ycombinator.com/item?id=46256343", "by": "hn_throw2025", "date": "2025-12-13", "stance": "recommend", "quote": "It's incredibly cheap and works reliably for me.", "excerpt": "I'm not the person you're replying to, but I use Whispering connected to the whisper-large-v3-turbo model on Groq. It's incredibly cheap and works reliably for me. I have got it to paste my voice transcriptions into Chrome (Gemini, Claude, ChatGPT) as well as Cursor. https://github.com/EpicenterHQ/epicenter", "context": "", "use_case": "hosting Whisper model inference", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}]}], "caveats": [{"label": "Policy changes", "summary": "One fan worries about the impact of recent changes, noting its no-data-storage default has ended.", "quotes": [{"id": 742493216, "item_id": 46405826, "url": "https://news.ycombinator.com/item?id=46405826", "by": "pjb88", "date": "2025-12-27", "stance": "recommend", "quote": "I'm a fan, and I use Groq a lot for systems I build.", "excerpt": "So... What will the actual impact on groq services be? I'm a fan, and I use Groq a lot for systems I build. I think they offer something different to most other providers (cheaper, faster, and until recently \"we don't store your data by default\") and it will be sad to see that fade.", "context": "builds systems using LLM APIs", "use_case": "LLM inference for built systems", "switched_from": "", "story": "Nvidia's $20B Antitrust Loophole (Not an Acquisition)"}]}, {"label": "Name confusion", "summary": "Easily confused with Grok, a different product.", "quotes": [{"id": 733371713, "item_id": 45835732, "url": "https://news.ycombinator.com/item?id=45835732", "by": "threeducks", "date": "2025-11-06", "stance": "recommend", "quote": "I used Groq (not to be confused with Grok), because it is free and very fast.", "excerpt": "While attempting to write my own script, I found that there are many websites which offer YouTube summaries, which are probably an easier solution. For example (not affiliated) https://www.easemate.ai/video-summary It even allows you to ask questions about the transcript. I also found a Python library for fetching YouTube video transcripts, but some issue mentioned that they got banned, so out of caution, I implement", "context": "", "use_case": "LLM API for summaries", "switched_from": "", "story": "I was right about dishwasher pods and now I can prove it [video]"}]}], "who": [{"by": "ImPrajyoth", "context": "Built an LLM process monitor", "url": "https://news.ycombinator.com/item?id=46435170", "date": "2025-12-30"}, {"by": "pjb88", "context": "builds systems using LLM APIs", "url": "https://news.ycombinator.com/item?id=46405826", "date": "2025-12-27"}], "tags": ["for LLM app builders", "for low-latency pipelines", "for voice transcription", "for LLM reranking"], "use_cases": ["privacy-conscious llm inference", "fast llm inference in scheduler", "llm inference for built systems", "llm inference", "model inference", "hosting whisper model inference"], "compared": [], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=46573860", "title": "Ask HN: Senior software engineers, how do you use Claude Code?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46435142", "title": "Show HN: Replacing my OS process scheduler with an LLM", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46403559", "title": "Nvidia's $20B Antitrust Loophole (Not an Acquisition)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46346026", "title": "Using Vectorize to build an unreasonably good search engine in 160 lines of code", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46357287", "title": "GLM-4.7: Advancing the Coding Capability", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46255285", "title": "Ask HN: How can I get better at using AI for programming?", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 1}, "2025-12": {"recommend": 4, "neutral": 1}, "2026-01": {"recommend": 1}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {}, "2026-08": {}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 745191440, "item_id": 46574465, "url": "https://news.ycombinator.com/item?id=46574465", "by": "allie1", "date": "2026-01-11", "stance": "recommend", "quote": "you can use an inference only solution like Groq.", "excerpt": "They are so wildly used, and the companies usually tell you if they use your prompts for training. But again, at the current use case your code gets lost in the noise even if they do use it. Anthropic says they don\u2019t. Microsoft allows you to disable, same with ChatGPT. Unclear on Goole. But if you are worried, you can use an inference only solution like Groq.", "context": "", "use_case": "privacy-conscious LLM inference", "switched_from": "", "story": "Ask HN: Senior software engineers, how do you use Claude Code?"}, {"id": 742962720, "item_id": 46435170, "url": "https://news.ycombinator.com/item?id=46435170", "by": "ImPrajyoth", "date": "2025-12-30", "stance": "recommend", "quote": "With Groq speed (Llama 3 @ 800t/s)", "excerpt": "OP here. this is a cursed project lol, but i wanted to see: What happens if you replace the OS scheduler with an LLM? With Groq speed (Llama 3 @ 800t/s), inference is finally fast enough to be in the system loop. i built this TUI to monitor my process tree. instead of just showing CPU %, it checks the context (parent process, disk I/O) to decide if a process is compiling code or bloatware. It roasts, throttles, or ki", "context": "Built an LLM process monitor", "use_case": "fast LLM inference in scheduler", "switched_from": "", "story": "Show HN: Replacing my OS process scheduler with an LLM"}, {"id": 742493216, "item_id": 46405826, "url": "https://news.ycombinator.com/item?id=46405826", "by": "pjb88", "date": "2025-12-27", "stance": "recommend", "quote": "I'm a fan, and I use Groq a lot for systems I build.", "excerpt": "So... What will the actual impact on groq services be? I'm a fan, and I use Groq a lot for systems I build. I think they offer something different to most other providers (cheaper, faster, and until recently \"we don't store your data by default\") and it will be sad to see that fade.", "context": "builds systems using LLM APIs", "use_case": "LLM inference for built systems", "switched_from": "", "story": "Nvidia's $20B Antitrust Loophole (Not an Acquisition)"}, {"id": 742139858, "item_id": 46383741, "url": "https://news.ycombinator.com/item?id=46383741", "by": "sgk284", "date": "2025-12-25", "stance": "recommend", "quote": "We use Groq with gpt-oss-20b, which gives great results and only adds ~250ms to the processing pipeline.", "excerpt": "Reranking is definitely the way to go. We personally found common reranker models to be a little too opaque (can't explain to the user why this result was picked) and not quite steerable enough, so we just use another LLM for reranking. We open-sourced our impl just this week: https://github.com/with-logic/intent We use Groq with gpt-oss-20b, which gives great results and only adds ~250ms to the processing pipeline. ", "context": "", "use_case": "LLM inference", "switched_from": "", "story": "Using Vectorize to build an unreasonably good search engine in 160 lines of code"}, {"id": 741769058, "item_id": 46360566, "url": "https://news.ycombinator.com/item?id=46360566", "by": "anonzzzies", "date": "2025-12-22", "stance": "neutral", "quote": "(or Groq with other models)", "excerpt": "I have been using 4.6 on Cerebras (or Groq with other models) since it dropped and it is a glimpse of the future. If AGI never happens but we manage to optimise things so I can run that on my handheld/tablet/laptop device, I am beyond happy. And I guess that might happen. Maybe with custom inference hardware like Cerebras. But seeing this generate at that speed is just jaw dropping.", "context": "", "use_case": "model inference", "switched_from": "", "story": "GLM-4.7: Advancing the Coding Capability"}, {"id": 740101490, "item_id": 46256343, "url": "https://news.ycombinator.com/item?id=46256343", "by": "hn_throw2025", "date": "2025-12-13", "stance": "recommend", "quote": "It's incredibly cheap and works reliably for me.", "excerpt": "I'm not the person you're replying to, but I use Whispering connected to the whisper-large-v3-turbo model on Groq. It's incredibly cheap and works reliably for me. I have got it to paste my voice transcriptions into Chrome (Gemini, Claude, ChatGPT) as well as Cursor. https://github.com/EpicenterHQ/epicenter", "context": "", "use_case": "hosting Whisper model inference", "switched_from": "", "story": "Ask HN: How can I get better at using AI for programming?"}, {"id": 733371713, "item_id": 45835732, "url": "https://news.ycombinator.com/item?id=45835732", "by": "threeducks", "date": "2025-11-06", "stance": "recommend", "quote": "I used Groq (not to be confused with Grok), because it is free and very fast.", "excerpt": "While attempting to write my own script, I found that there are many websites which offer YouTube summaries, which are probably an easier solution. For example (not affiliated) https://www.easemate.ai/video-summary It even allows you to ask questions about the transcript. I also found a Python library for fetching YouTube video transcripts, but some issue mentioned that they got banned, so out of caution, I implement", "context": "", "use_case": "LLM API for summaries", "switched_from": "", "story": "I was right about dishwasher pods and now I can prove it [video]"}]}