{"slug": "gemini-flash", "name": "Gemini Flash", "category": "ai", "category_name": "AI models and assistants", "description": "Google's fast, lower-cost Gemini large language model tier, available via the Gemini app and API.", "recommenders": 63, "commenters": 116, "warners": 17, "score": 51.388, "rising": 30.49, "first": "2025-12-18", "latest": "2026-10-29", "why": "HN commenters use it as a fast, low-cost daily driver for coding and research, often executing plans written by a stronger model.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 71, "neutral": 29, "compare": 10, "warn": 17}, "spark": [0, 4, 4, 4, 1, 5, 0, 3, 9, 12, 20, 9], "listed": true, "loved": ["Speed", "Coding"], "caveat": "Usage limits", "short_quote": "I love the new Gemini 3 Flash model - it hits so many sweet-spots for me.", "icon": true, "domain": null, "github_repo": "github.com/modelrift/openscad-skill", "official_url": "https://deepmind.google/models/gemini/flash/", "pricing": "freemium", "aliases": ["Gemini 3 Flash", "Gemini Flash", "Gemini 3.8 Flash", "Gemini 3.5 Flash", "Gemini 3.7 Flash", "Gemini 3.6 Flash", "Gemini Flash 3.8"], "verdict": [{"text": "HN commenters use it as a fast, low-cost daily driver for coding and research,", "cites": [{"id": 804451456, "item_id": 50278216, "url": "https://news.ycombinator.com/item?id=50278216", "by": "mattlondon", "date": "2026-10-28", "stance": "recommend", "quote": "3.8 Flash has been my favourite model and daily driver for a little while now.", "excerpt": "Agreed. I was really looking forward to 4 Flash. 3.8 Flash has been my favourite model and daily driver for a little while now. But to be honest I am now not sure if Argon was the flash model and this Carbon is pro? It's very confusing.", "context": "", "use_case": "everyday use", "switched_from": "", "story": "Gemini 4 Carbon"}, {"id": 803853441, "item_id": 50240840, "url": "https://news.ycombinator.com/item?id=50240840", "by": "mattlondon", "date": "2026-10-26", "stance": "recommend", "quote": "I use Gemini 3.8 Flash as my daily driver for most coding.", "excerpt": "I think, despite the desperate attempt at IBM to remain relevant (and in business), their CEO has a point here that do you really need SOTA models for everything? I had a really nice time with GLM5.2 for a month or two - it was, in my experience, approx Opus 4.5ish level of capability when I think Opus 4.8 was the new hotness Even today, I use Gemini 3.8 Flash as my daily driver for most coding. Its fast and good, ev", "context": "", "use_case": "daily coding", "switched_from": "", "story": "IBM CEO says open weight models are now good and cheap on-prem"}, {"id": 792976864, "item_id": 49561054, "url": "https://news.ycombinator.com/item?id=49561054", "by": "conception", "date": "2026-09-04", "stance": "recommend", "quote": "Flash 3.8 is rad. Easily my daily driver now.", "excerpt": "Flash 3.8 is rad. Easily my daily driver now. Only downside is it's Gemini so sometimes it just keeps going until it wants to be done.", "context": "", "use_case": "daily driver model", "switched_from": "", "story": "GPT-6 Astra"}, {"id": 795165632, "item_id": 49697852, "url": "https://news.ycombinator.com/item?id=49697852", "by": "ipsod", "date": "2026-09-14", "stance": "recommend", "quote": "It's ridiculously fast, and generally very good with real-world knowledge.", "excerpt": "It's ridiculously fast, and generally very good with real-world knowledge. It's my go-to for anything non-coding, and for quick fixes/questions/prototypes. If metrics measured what most people need from an LLM, it's competitive, IMO, and with their TPU chips, it's probably economically competitive.", "context": "", "use_case": "non-coding questions, quick prototypes", "switched_from": "", "story": "Why is Google still serving dodgy ads?"}, {"id": 788324113, "item_id": 49270257, "url": "https://news.ycombinator.com/item?id=49270257", "by": "antonvs", "date": "2026-08-12", "stance": "recommend", "quote": "It\u2019s very competent, and quite a bit cheaper than Claude.", "excerpt": "How are you accessing it? You may be using one of the limited models. I use Gemini Antigravity daily for software design and coding, mostly using the Gemini 3.5 Flash model. It\u2019s very competent, and quite a bit cheaper than Claude.", "context": "", "use_case": "software design and coding", "switched_from": "", "story": "Gemini becomes Google's fastest-growing product ever as it hits 1B users"}]}, {"text": " often executing plans written by a stronger model.", "cites": [{"id": 798687056, "item_id": 49917941, "url": "https://news.ycombinator.com/item?id=49917941", "by": "lp92", "date": "2026-10-01", "stance": "recommend", "quote": "3.8 Flash does really well for writing code as long as you give it a good design and plan to follow.", "excerpt": "Same! 3.8 Flash does really well for writing code as long as you give it a good design and plan to follow. I use Opus for architecture/design/implementation plans and let Gemini 3.8 work using those. Even on the $20 Pro plan I've only come down to 10% before the weekly reset.", "context": "on the $20 Pro plan", "use_case": "implementing code from plans", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 798532000, "item_id": 49908250, "url": "https://news.ycombinator.com/item?id=49908250", "by": "lp92", "date": "2026-09-30", "stance": "recommend", "quote": "Currently I'm building my own generative modeling + aero sim package largely using Gemini and it's been working great.", "excerpt": "Since Gemini 3.8 Flash release, I've been largely using that for my coding ttasks. The architectureand design work I use Opus, but the rest of the work is done via Gemini 3.8. I don'thave to worry aboutweekly limits even on the $20 plan. I get down to about 10% weekly limit before it resets. Currently I'm building my own generative modeling + aero sim package largely using Gemini and it's been working great.", "context": "building a generative modeling and aero sim package", "use_case": "most coding tasks", "switched_from": "", "story": "GPT-6.1 Sol replaces GPT-6 Sol after just 7 days, with near-Astra intelligence"}, {"id": 798645042, "item_id": 49915315, "url": "https://news.ycombinator.com/item?id=49915315", "by": "huydotnet", "date": "2026-09-30", "stance": "recommend", "quote": "If there's already a detailed plan, 3.7 can complete the task much faster.", "excerpt": "I recently subscribed to Claude, and was very unhappy about the usage limit of the $20 pro plan. Then I found a trick, since I got free Google AI Pro via my phone carrier, I use Opus 5.5 High for planning, and then dispatching agy to do works. Most of the time 3.8 works fine, but it's a bit slow if compare to 3.7 Flash. If there's already a detailed plan, 3.7 can complete the task much faster. And the best thing abou", "context": "", "use_case": "executing detailed plans", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 792613152, "item_id": 49538322, "url": "https://news.ycombinator.com/item?id=49538322", "by": "datlife", "date": "2026-09-02", "stance": "recommend", "quote": "I use Flash model as code implementation executor, then have GPT-5.6-Sol or Opus to review the work.", "excerpt": "I use Flash model as code implementation executor, then have GPT-5.6-Sol or Opus to review the work. Pretty good so far and presumably less expensive.", "context": "", "use_case": "code implementation", "switched_from": "", "story": "Gemini 3.8 Flash and 3.8 Flash Cyber"}]}, {"text": " The most common complaints are tight usage limits and flaky availability,", "cites": [{"id": 790646353, "item_id": 49415397, "url": "https://news.ycombinator.com/item?id=49415397", "by": "DefamationStati", "date": "2026-08-24", "stance": "warn", "quote": "the limits as absolutely abysmal when using 3.7 flash in antigravity", "excerpt": "I've got the AI pro plan for Gemini and the limits as absolutely abysmal when using 3.7 flash in antigravity, If I use swarms then I can't even finish a single prompt without it reaching the limit.", "context": "has Gemini AI Pro plan", "use_case": "AI coding", "switched_from": "", "story": "Anthropic's best AI model struggles to attract users as cheaper tools thrive"}, {"id": 788636224, "item_id": 49289764, "url": "https://news.ycombinator.com/item?id=49289764", "by": "UncleOxidant", "date": "2026-08-13", "stance": "recommend", "quote": "Yes, 3.6 Flash is very fast.", "excerpt": "Yes, 3.6 Flash is very fast. I used to get a fair amount of usage of the Gemini Flash models on the free tier. I signed up for their $4.99/month tier (includes 400GB of Google space which was also enticing) and it turns out I only get about 15 to 20 minutes of usage before I get a come-back-in-7-days message. Comically low usage limits on that plan.", "context": "", "use_case": "general use", "switched_from": "", "story": "Gemini 3.7 Flash"}, {"id": 803856464, "item_id": 50241029, "url": "https://news.ycombinator.com/item?id=50241029", "by": "jaccola", "date": "2026-10-26", "stance": "warn", "quote": "I love 3.8 Flash, if only it weren\u2019t unusably flaky.", "excerpt": "I love 3.8 Flash, if only it weren\u2019t unusably flaky. Sometimes simple responses take minutes or I get rate limited after sending a single message (I guess it\u2019s a shared pool rate limit). Have you not experienced this (would love to know if there\u2019s a way to actually use it reliably!)", "context": "", "use_case": "coding", "switched_from": "", "story": "IBM CEO says open weight models are now good and cheap on-prem"}, {"id": 783097250, "item_id": 48943578, "url": "https://news.ycombinator.com/item?id=48943578", "by": "arman-w-jalili", "date": "2026-07-16", "stance": "warn", "quote": "i casually get error, api not available, especially gemeni-flash", "excerpt": "at the moment private i use mainly deepseek, about 80% and very very happy with it, at work we have copilot, i'm not sure, but the quality of service has got degraded in my opinion, speed is very low, i casually get error, api not available, especially gemeni-flash ,i have the feeling GPT5.4 is not as good as before, and with serious work i burn all my 400\u20ac budget in 4 days", "context": "", "use_case": "work LLM via Copilot", "switched_from": "", "story": "What % of your usage is open source vs. frontier models?"}]}, {"text": " and several say it struggles with long-horizon work and heavy refactors.", "cites": [{"id": 788628736, "item_id": 49289296, "url": "https://news.ycombinator.com/item?id=49289296", "by": "fmind-dev", "date": "2026-08-13", "stance": "recommend", "quote": "Gemini Flash is one of the best \"good-enough\" models.", "excerpt": "Gemini Flash is one of the best \"good-enough\" models. I use this type of model daily, for automation and quick development iteration loops. Unfortunately, it's often not strong enough for heavy refactoring and long running development loops.", "context": "", "use_case": "automation and quick dev iteration loops", "switched_from": "", "story": "Gemini 3.7 Flash"}, {"id": 795571712, "item_id": 49723232, "url": "https://news.ycombinator.com/item?id=49723232", "by": "TomGarden", "date": "2026-09-16", "stance": "recommend", "quote": "3.8 flash is the best back-and-forth model for iterating imo", "excerpt": "I love it as a variation from the others. 3.8 flash is the best back-and-forth model for iterating imo, but would not use for long horizon", "context": "", "use_case": "iterating back-and-forth", "switched_from": "", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 801194497, "item_id": 50074656, "url": "https://news.ycombinator.com/item?id=50074656", "by": "eluusive", "date": "2026-10-13", "stance": "warn", "quote": "Almost everything had been stubbed out by 3.8, and none of it was properly integrated into the codebase.", "excerpt": "Just switched, and it seems to be much better. I'm hoping it stops lying. I have Pro max subs for Claude, Codex, Grok, and Google AI... I was forced into using Google by running out of credits elsewhere. I have found that Gemini often claims it did something, but didn't actually complete the task. I just had 3.8 Flash do a major refactor -- that never should have needed to be done in the first place -- and switched t", "context": "has Pro max subs for Claude, Codex, Grok, and Google AI", "use_case": "code refactoring", "switched_from": "", "story": "Gemini 4 Argon"}]}], "praise": [{"label": "Speed", "summary": "Commenters repeatedly describe it as very fast, which makes quick iteration pleasant.", "quotes": [{"id": 795165632, "item_id": 49697852, "url": "https://news.ycombinator.com/item?id=49697852", "by": "ipsod", "date": "2026-09-14", "stance": "recommend", "quote": "It's ridiculously fast, and generally very good with real-world knowledge.", "excerpt": "It's ridiculously fast, and generally very good with real-world knowledge. It's my go-to for anything non-coding, and for quick fixes/questions/prototypes. If metrics measured what most people need from an LLM, it's competitive, IMO, and with their TPU chips, it's probably economically competitive.", "context": "", "use_case": "non-coding questions, quick prototypes", "switched_from": "", "story": "Why is Google still serving dodgy ads?"}, {"id": 783901280, "item_id": 48993830, "url": "https://news.ycombinator.com/item?id=48993830", "by": "uejfiweun", "date": "2026-07-21", "stance": "recommend", "quote": "when I want a very quick response, my go-to is Gemini Flash. It's just really damn fast", "excerpt": "I know that Flash is obviously no Opus or Fable. That being said, when I want a very quick response, my go-to is Gemini Flash. It's just really damn fast and generally tends to be accurate enough.", "context": "", "use_case": "quick responses", "switched_from": "", "story": "Gemini 3.6 Flash"}, {"id": 791292816, "item_id": 49455801, "url": "https://news.ycombinator.com/item?id=49455801", "by": "smartbit", "date": "2026-08-26", "stance": "recommend", "quote": "Working with de speed of Gemini 3.7 Flash is such a delight", "excerpt": "Looking at these numbers IMHO, with Gemini you get the speed what you pay for. Intel Cost lig per ence Task Speed Gemini 3.7 flash 56 0.40 338 GLM 5.3 flash 57 0.09 49 Factor 1 4.4 6.9 I have both GLM & Gemini in a subscription and see no reason for choosing GLM 5.3 Flash. Working with de speed of Gemini 3.7 Flash is such a delight that I accept the hassle of working with Antigravity CLI, coming from Claude Code whic", "context": "", "use_case": "fast coding model", "switched_from": "", "story": "GLM-5.3-Flash Intelligence, Performance and Price Analysis"}]}, {"label": "Coding", "summary": "Many use it for most of their coding and say it does solid work, especially with a clear plan.", "quotes": [{"id": 803853441, "item_id": 50240840, "url": "https://news.ycombinator.com/item?id=50240840", "by": "mattlondon", "date": "2026-10-26", "stance": "recommend", "quote": "I use Gemini 3.8 Flash as my daily driver for most coding.", "excerpt": "I think, despite the desperate attempt at IBM to remain relevant (and in business), their CEO has a point here that do you really need SOTA models for everything? I had a really nice time with GLM5.2 for a month or two - it was, in my experience, approx Opus 4.5ish level of capability when I think Opus 4.8 was the new hotness Even today, I use Gemini 3.8 Flash as my daily driver for most coding. Its fast and good, ev", "context": "", "use_case": "daily coding", "switched_from": "", "story": "IBM CEO says open weight models are now good and cheap on-prem"}, {"id": 798687056, "item_id": 49917941, "url": "https://news.ycombinator.com/item?id=49917941", "by": "lp92", "date": "2026-10-01", "stance": "recommend", "quote": "3.8 Flash does really well for writing code as long as you give it a good design and plan to follow.", "excerpt": "Same! 3.8 Flash does really well for writing code as long as you give it a good design and plan to follow. I use Opus for architecture/design/implementation plans and let Gemini 3.8 work using those. Even on the $20 Pro plan I've only come down to 10% before the weekly reset.", "context": "on the $20 Pro plan", "use_case": "implementing code from plans", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 794843024, "item_id": 49677689, "url": "https://news.ycombinator.com/item?id=49677689", "by": "tucnak", "date": "2026-09-12", "stance": "recommend", "quote": "I use 3.8 flash in Antigravity a lot, and thoroughly prefer it to most Pro-class models.", "excerpt": "Hard disagree. I use 3.8 flash in Antigravity a lot, and thoroughly prefer it to most Pro-class models. It's really fast, and I've had it make crazy progress on compiler-like problems that previous models including Opus simply failed at. On ultra plan you can have it going for hours, and make incremental progress with good prompting for review interrupts. It solved a problem I couldn't solve for weeks in under 6 hour", "context": "", "use_case": "compiler-like coding problems", "switched_from": "", "story": "Real-SWE: Benchmarking AI models on private, real-world, enterprise codebases"}]}, {"label": "Low cost", "summary": "Users call it cheap or nearly free, with quotas that go far on lower-priced plans.", "quotes": [{"id": 798646784, "item_id": 49915424, "url": "https://news.ycombinator.com/item?id=49915424", "by": "gcy", "date": "2026-09-30", "stance": "recommend", "quote": "it's fast and almost free (sufficient quota with pro account)", "excerpt": "I use 3.8 Flash for daily troubleshooting tasks e.g. help me find out why certain app crashes or certain website does not load normally with playwright-cli. Sure it's not as capable but it's fast and almost free (sufficient quota with pro account). The only thing that bugs me is that I need to use `--dangerously-skip-permissions` as it does not have auto review.", "context": "", "use_case": "daily troubleshooting", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 788324113, "item_id": 49270257, "url": "https://news.ycombinator.com/item?id=49270257", "by": "antonvs", "date": "2026-08-12", "stance": "recommend", "quote": "It\u2019s very competent, and quite a bit cheaper than Claude.", "excerpt": "How are you accessing it? You may be using one of the limited models. I use Gemini Antigravity daily for software design and coding, mostly using the Gemini 3.5 Flash model. It\u2019s very competent, and quite a bit cheaper than Claude.", "context": "", "use_case": "software design and coding", "switched_from": "", "story": "Gemini becomes Google's fastest-growing product ever as it hits 1B users"}, {"id": 787634193, "item_id": 49227137, "url": "https://news.ycombinator.com/item?id=49227137", "by": "FpUser", "date": "2026-08-08", "stance": "recommend", "quote": "I use Junie straight from my JetBrain's IDEs that in turn uses Gemini Flash. Very cheap and more than enough for my use.", "excerpt": ">\"To what extent are the Chinese labs being subsidized? Are they real businesses?\" And who gives a flying fuck. I am a \"real\" business and I count my money. It is not my life goal to prop some fat cats crying crocodile tears. Granted I do not use Chinese models. I use Junie straight from my JetBrain's IDEs that in turn uses Gemini Flash. Very cheap and more than enough for my use.", "context": "runs a business, cost-conscious", "use_case": "AI coding model", "switched_from": "", "story": "DeepSeek V4 Flash 0731"}]}, {"label": "Daily driver", "summary": "Several commenters say it has become their favourite everyday model.", "quotes": [{"id": 804451456, "item_id": 50278216, "url": "https://news.ycombinator.com/item?id=50278216", "by": "mattlondon", "date": "2026-10-28", "stance": "recommend", "quote": "3.8 Flash has been my favourite model and daily driver for a little while now.", "excerpt": "Agreed. I was really looking forward to 4 Flash. 3.8 Flash has been my favourite model and daily driver for a little while now. But to be honest I am now not sure if Argon was the flash model and this Carbon is pro? It's very confusing.", "context": "", "use_case": "everyday use", "switched_from": "", "story": "Gemini 4 Carbon"}, {"id": 792976864, "item_id": 49561054, "url": "https://news.ycombinator.com/item?id=49561054", "by": "conception", "date": "2026-09-04", "stance": "recommend", "quote": "Flash 3.8 is rad. Easily my daily driver now.", "excerpt": "Flash 3.8 is rad. Easily my daily driver now. Only downside is it's Gemini so sometimes it just keeps going until it wants to be done.", "context": "", "use_case": "daily driver model", "switched_from": "", "story": "GPT-6 Astra"}, {"id": 783919248, "item_id": 48994953, "url": "https://news.ycombinator.com/item?id=48994953", "by": "dakolli", "date": "2026-07-21", "stance": "recommend", "quote": "I use 3.5 flash 10x more than any other model", "excerpt": "I use 3.5 flash 10x more than any other model, despite have access to all of them. If I'm going to play a slot machine, I'd rather get the pain over with quickly.", "context": "", "use_case": "general AI use", "switched_from": "", "story": "Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber"}]}, {"label": "Research and knowledge", "summary": "Praised for web-search-style queries, real-world knowledge and general research.", "quotes": [{"id": 800299664, "item_id": 50018729, "url": "https://news.ycombinator.com/item?id=50018729", "by": "dada216", "date": "2026-10-09", "stance": "recommend", "quote": "for what amounts to a web search Gemini 3.8 flash is better than the big models", "excerpt": "I even find that for what amounts to a web search Gemini 3.8 flash is better than the big models, stuff like the links to updated tax codes in different countries, or whatever MS is doing with Azure/o365 or AWS with their plethora of products. I think use cases are the real reason why people have such different experiences, I too find that Opus5.5/Astra/6 are better for UI/UX now, it wasn't the case a year ago, at so", "context": "", "use_case": "web search style queries", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 792627440, "item_id": 49539215, "url": "https://news.ycombinator.com/item?id=49539215", "by": "ipsod", "date": "2026-09-02", "stance": "recommend", "quote": "Gemini Flash is the one I get most excited about, because it's so fast and so good at real-world knowledge", "excerpt": "Gemini Flash is the one I get most excited about, because it's so fast and so good at real-world knowledge, and it's improving so fast - look at how much the benchmarks improved in ~1 month. It's just categorically different than anything else. Also, I use it every day, and it just got ~10% better at coding, according to the benchmarks. How is that not exciting?", "context": "", "use_case": "daily use and coding", "switched_from": "", "story": "Gemini 3.8 Flash and 3.8 Flash Cyber"}, {"id": 783896465, "item_id": 48993529, "url": "https://news.ycombinator.com/item?id=48993529", "by": "glimshe", "date": "2026-07-21", "stance": "recommend", "quote": "excellent model for general (re)search.", "excerpt": "I respectfully disagree, at least for most tasks. 3.1 Pro: while it's coding performance is mediocre, a lot of coding work requires minimum actual thinking. I use it often for light refactoring, boilerplate generation, testcase skeleton generation, code review, language questions (\"is there a better way to write this code block?\"). I don't have a corporation behind me so costs matter. Considering that I'm a Pro subsc", "context": "Pro subscriber without a corporation behind them", "use_case": "general search and everyday tasks", "switched_from": "", "story": "Gemini 3.6 Flash"}]}, {"label": "Plan executor", "summary": "Commonly paired with Opus or similar for planning or review while Flash does the implementation.", "quotes": [{"id": 798532000, "item_id": 49908250, "url": "https://news.ycombinator.com/item?id=49908250", "by": "lp92", "date": "2026-09-30", "stance": "recommend", "quote": "Currently I'm building my own generative modeling + aero sim package largely using Gemini and it's been working great.", "excerpt": "Since Gemini 3.8 Flash release, I've been largely using that for my coding ttasks. The architectureand design work I use Opus, but the rest of the work is done via Gemini 3.8. I don'thave to worry aboutweekly limits even on the $20 plan. I get down to about 10% weekly limit before it resets. Currently I'm building my own generative modeling + aero sim package largely using Gemini and it's been working great.", "context": "building a generative modeling and aero sim package", "use_case": "most coding tasks", "switched_from": "", "story": "GPT-6.1 Sol replaces GPT-6 Sol after just 7 days, with near-Astra intelligence"}, {"id": 798645042, "item_id": 49915315, "url": "https://news.ycombinator.com/item?id=49915315", "by": "huydotnet", "date": "2026-09-30", "stance": "recommend", "quote": "If there's already a detailed plan, 3.7 can complete the task much faster.", "excerpt": "I recently subscribed to Claude, and was very unhappy about the usage limit of the $20 pro plan. Then I found a trick, since I got free Google AI Pro via my phone carrier, I use Opus 5.5 High for planning, and then dispatching agy to do works. Most of the time 3.8 works fine, but it's a bit slow if compare to 3.7 Flash. If there's already a detailed plan, 3.7 can complete the task much faster. And the best thing abou", "context": "", "use_case": "executing detailed plans", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 792613152, "item_id": 49538322, "url": "https://news.ycombinator.com/item?id=49538322", "by": "datlife", "date": "2026-09-02", "stance": "recommend", "quote": "I use Flash model as code implementation executor, then have GPT-5.6-Sol or Opus to review the work.", "excerpt": "I use Flash model as code implementation executor, then have GPT-5.6-Sol or Opus to review the work. Pretty good so far and presumably less expensive.", "context": "", "use_case": "code implementation", "switched_from": "", "story": "Gemini 3.8 Flash and 3.8 Flash Cyber"}]}], "caveats": [{"label": "Usage limits", "summary": "Some subscribers hit rate limits or quotas very quickly.", "quotes": [{"id": 790646353, "item_id": 49415397, "url": "https://news.ycombinator.com/item?id=49415397", "by": "DefamationStati", "date": "2026-08-24", "stance": "warn", "quote": "the limits as absolutely abysmal when using 3.7 flash in antigravity", "excerpt": "I've got the AI pro plan for Gemini and the limits as absolutely abysmal when using 3.7 flash in antigravity, If I use swarms then I can't even finish a single prompt without it reaching the limit.", "context": "has Gemini AI Pro plan", "use_case": "AI coding", "switched_from": "", "story": "Anthropic's best AI model struggles to attract users as cheaper tools thrive"}, {"id": 788636224, "item_id": 49289764, "url": "https://news.ycombinator.com/item?id=49289764", "by": "UncleOxidant", "date": "2026-08-13", "stance": "recommend", "quote": "Yes, 3.6 Flash is very fast.", "excerpt": "Yes, 3.6 Flash is very fast. I used to get a fair amount of usage of the Gemini Flash models on the free tier. I signed up for their $4.99/month tier (includes 400GB of Google space which was also enticing) and it turns out I only get about 15 to 20 minutes of usage before I get a come-back-in-7-days message. Comically low usage limits on that plan.", "context": "", "use_case": "general use", "switched_from": "", "story": "Gemini 3.7 Flash"}, {"id": 803856464, "item_id": 50241029, "url": "https://news.ycombinator.com/item?id=50241029", "by": "jaccola", "date": "2026-10-26", "stance": "warn", "quote": "I love 3.8 Flash, if only it weren\u2019t unusably flaky.", "excerpt": "I love 3.8 Flash, if only it weren\u2019t unusably flaky. Sometimes simple responses take minutes or I get rate limited after sending a single message (I guess it\u2019s a shared pool rate limit). Have you not experienced this (would love to know if there\u2019s a way to actually use it reliably!)", "context": "", "use_case": "coding", "switched_from": "", "story": "IBM CEO says open weight models are now good and cheap on-prem"}]}, {"label": "Flaky service", "summary": "Users report slow responses and API-unavailable errors.", "quotes": [{"id": 803856464, "item_id": 50241029, "url": "https://news.ycombinator.com/item?id=50241029", "by": "jaccola", "date": "2026-10-26", "stance": "warn", "quote": "I love 3.8 Flash, if only it weren\u2019t unusably flaky.", "excerpt": "I love 3.8 Flash, if only it weren\u2019t unusably flaky. Sometimes simple responses take minutes or I get rate limited after sending a single message (I guess it\u2019s a shared pool rate limit). Have you not experienced this (would love to know if there\u2019s a way to actually use it reliably!)", "context": "", "use_case": "coding", "switched_from": "", "story": "IBM CEO says open weight models are now good and cheap on-prem"}, {"id": 783097250, "item_id": 48943578, "url": "https://news.ycombinator.com/item?id=48943578", "by": "arman-w-jalili", "date": "2026-07-16", "stance": "warn", "quote": "i casually get error, api not available, especially gemeni-flash", "excerpt": "at the moment private i use mainly deepseek, about 80% and very very happy with it, at work we have copilot, i'm not sure, but the quality of service has got degraded in my opinion, speed is very low, i casually get error, api not available, especially gemeni-flash ,i have the feeling GPT5.4 is not as good as before, and with serious work i burn all my 400\u20ac budget in 4 days", "context": "", "use_case": "work LLM via Copilot", "switched_from": "", "story": "What % of your usage is open source vs. frontier models?"}]}, {"label": "Long, heavy tasks", "summary": "Said to be weaker for long-horizon work and large refactors.", "quotes": [{"id": 788628736, "item_id": 49289296, "url": "https://news.ycombinator.com/item?id=49289296", "by": "fmind-dev", "date": "2026-08-13", "stance": "recommend", "quote": "Gemini Flash is one of the best \"good-enough\" models.", "excerpt": "Gemini Flash is one of the best \"good-enough\" models. I use this type of model daily, for automation and quick development iteration loops. Unfortunately, it's often not strong enough for heavy refactoring and long running development loops.", "context": "", "use_case": "automation and quick dev iteration loops", "switched_from": "", "story": "Gemini 3.7 Flash"}, {"id": 795571712, "item_id": 49723232, "url": "https://news.ycombinator.com/item?id=49723232", "by": "TomGarden", "date": "2026-09-16", "stance": "recommend", "quote": "3.8 flash is the best back-and-forth model for iterating imo", "excerpt": "I love it as a variation from the others. 3.8 flash is the best back-and-forth model for iterating imo, but would not use for long horizon", "context": "", "use_case": "iterating back-and-forth", "switched_from": "", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 801194497, "item_id": 50074656, "url": "https://news.ycombinator.com/item?id=50074656", "by": "eluusive", "date": "2026-10-13", "stance": "warn", "quote": "Almost everything had been stubbed out by 3.8, and none of it was properly integrated into the codebase.", "excerpt": "Just switched, and it seems to be much better. I'm hoping it stops lying. I have Pro max subs for Claude, Codex, Grok, and Google AI... I was forced into using Google by running out of credits elsewhere. I have found that Gemini often claims it did something, but didn't actually complete the task. I just had 3.8 Flash do a major refactor -- that never should have needed to be done in the first place -- and switched t", "context": "has Pro max subs for Claude, Codex, Grok, and Google AI", "use_case": "code refactoring", "switched_from": "", "story": "Gemini 4 Argon"}]}, {"label": "Accuracy slips", "summary": "Some saw it claim finished work it had stubbed out or misread its own context.", "quotes": [{"id": 801194497, "item_id": 50074656, "url": "https://news.ycombinator.com/item?id=50074656", "by": "eluusive", "date": "2026-10-13", "stance": "warn", "quote": "Almost everything had been stubbed out by 3.8, and none of it was properly integrated into the codebase.", "excerpt": "Just switched, and it seems to be much better. I'm hoping it stops lying. I have Pro max subs for Claude, Codex, Grok, and Google AI... I was forced into using Google by running out of credits elsewhere. I have found that Gemini often claims it did something, but didn't actually complete the task. I just had 3.8 Flash do a major refactor -- that never should have needed to be done in the first place -- and switched t", "context": "has Pro max subs for Claude, Codex, Grok, and Google AI", "use_case": "code refactoring", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 788638720, "item_id": 49289920, "url": "https://news.ycombinator.com/item?id=49289920", "by": "eckr", "date": "2026-08-13", "stance": "warn", "quote": "have people had trouble with 3.6 Flash just... getting things it has seen in its context correct?", "excerpt": "Maybe this is just my experience, but have people had trouble with 3.6 Flash just... getting things it has seen in its context correct? I don't know if it's been insanely benchmaxxed or what, but it'll pull information from websites and immediately get it wrong the token after. Or for example (this is something that happened like yesterday) I asked it to compare the uses of A and B in a language I was learning, and t", "context": "", "use_case": "", "switched_from": "", "story": "Gemini 3.7 Flash"}]}, {"label": "Harness friction", "summary": "Commenters dislike Google's harnesses and the limits on using it in their own tools.", "quotes": [{"id": 793915104, "item_id": 49619694, "url": "https://news.ycombinator.com/item?id=49619694", "by": "artdigital", "date": "2026-09-09", "stance": "recommend", "quote": "Gemini Flash 3.8 is an awesome model! I use it all the time", "excerpt": "More because Spark is not good. Gemini Flash 3.8 is an awesome model! I use it all the time Spark asks you for every single tool call, often forgets earlier parts of the conversation, is unable to use apps unless you explicitly tag them and and and Google has great models, but their harnesses and products are just bad", "context": "", "use_case": "general AI model use", "switched_from": "", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 788825424, "item_id": 49301589, "url": "https://news.ycombinator.com/item?id=49301589", "by": "nxdmum", "date": "2026-08-14", "stance": "recommend", "quote": "By the way - I love Gemini's personality . it's phenomenal to work with", "excerpt": "Simple question - can i use Gemini 3.7 flash with a subscription in my own harness and not in agy client ? You're from Google so the question. By the way - I love Gemini's personality . it's phenomenal to work with The reason i want my own harness - is the custom tools that i provide vs the low tier tools that come with the custom harnesses. You'll would really benefit , if we could use Gemini in our own harness and ", "context": "", "use_case": "custom coding harness", "switched_from": "", "story": "Gemini 3.7 Flash"}, {"id": 798646784, "item_id": 49915424, "url": "https://news.ycombinator.com/item?id=49915424", "by": "gcy", "date": "2026-09-30", "stance": "recommend", "quote": "it's fast and almost free (sufficient quota with pro account)", "excerpt": "I use 3.8 Flash for daily troubleshooting tasks e.g. help me find out why certain app crashes or certain website does not load normally with playwright-cli. Sure it's not as capable but it's fast and almost free (sufficient quota with pro account). The only thing that bugs me is that I need to use `--dangerously-skip-permissions` as it does not have auto review.", "context": "", "use_case": "daily troubleshooting", "switched_from": "", "story": "Gemini 4 Argon"}]}, {"label": "Pricing changes", "summary": "Some worry about newer Flash versions being pricier and about announced price increases.", "quotes": [{"id": 781857089, "item_id": 48866068, "url": "https://news.ycombinator.com/item?id=48866068", "by": "zuzululu", "date": "2026-07-10", "stance": "warn", "quote": "gemini 3 flash is expensive", "excerpt": "sucks we use 2.5 flash/lite in our company it handles millions of requests a day theres nothing in its price range that provides the same all around perf as noted, gemini 3 flash is expensive really not liking google these days they are not hungry anymore", "context": "", "use_case": "", "switched_from": "", "story": "Don't discontinue Gemini 2.5 Flash"}, {"id": 788627552, "item_id": 49289222, "url": "https://news.ycombinator.com/item?id=49289222", "by": "npn", "date": "2026-08-13", "stance": "warn", "quote": "nobody would use flash 3.7 at that time.", "excerpt": "> * For 3.6 and 3.7 Flash, introductory price expires on December 31, 2026. Starting January 1, 2027, $1.50/1M input tokens and $7.50/1M output tokens will apply. this is hilarious. it is not 2025 any more, by Jan 2027 there will be at least 3 newer generation of models (from other provider) released already. nobody would use flash 3.7 at that time. sure we used to cling to gemini models in the past, demanding 2.5 mo", "context": "", "use_case": "", "switched_from": "", "story": "Gemini 3.7 Flash"}]}], "who": [{"by": "conception", "context": "bounces around models as soon as they come out", "url": "https://news.ycombinator.com/item?id=50296895", "date": "2026-10-29"}, {"by": "Revanche1367", "context": "AI Ultra plan subscriber", "url": "https://news.ycombinator.com/item?id=50294078", "date": "2026-10-29"}, {"by": "freakynit", "context": "Gemini Pro subscriber", "url": "https://news.ycombinator.com/item?id=50074494", "date": "2026-10-13"}, {"by": "lp92", "context": "on the $20 Pro plan", "url": "https://news.ycombinator.com/item?id=49917941", "date": "2026-10-01"}, {"by": "toshvelaga", "context": "built a healthcare LLM benchmark", "url": "https://news.ycombinator.com/item?id=49631768", "date": "2026-09-09"}, {"by": "hakunin", "context": "built a personal doc tool", "url": "https://news.ycombinator.com/item?id=49610351", "date": "2026-09-08"}, {"by": "a11r", "context": "uses it in production", "url": "https://news.ycombinator.com/item?id=49538445", "date": "2026-09-02"}, {"by": "doix", "context": "non-professional projects", "url": "https://news.ycombinator.com/item?id=49518428", "date": "2026-09-01"}, {"by": "mikeushakov", "context": "PhD candidate in social sciences", "url": "https://news.ycombinator.com/item?id=49509661", "date": "2026-08-31"}, {"by": "ltrg", "context": "builds research agents for methane plume attribution", "url": "https://news.ycombinator.com/item?id=49389966", "date": "2026-08-21"}, {"by": "FpUser", "context": "runs a business, cost-conscious", "url": "https://news.ycombinator.com/item?id=49227137", "date": "2026-08-08"}, {"by": "glimshe", "context": "Pro subscriber without a corporation behind them", "url": "https://news.ycombinator.com/item?id=48993529", "date": "2026-07-21"}], "tags": ["for agentic coding", "for quick research", "for cost-conscious devs", "free tier available", "for document and video processing"], "use_cases": ["coding", "daily driver model", "coding agent tasks", "ai coding", "software development", "general llm use"], "compared": [{"slug": "gemini-pro", "name": "Gemini Pro", "co": 23, "switched_from": 2, "switched_to": 2}, {"slug": "claude-opus", "name": "Claude Opus", "co": 27, "switched_from": 0, "switched_to": 0}, {"slug": "claude-sonnet", "name": "Claude Sonnet", "co": 7, "switched_from": 1, "switched_to": 1}, {"slug": "claude", "name": "Claude", "co": 9, "switched_from": 1, "switched_to": 0}, {"slug": "claude-code", "name": "Claude Code", "co": 10, "switched_from": 0, "switched_to": 0}, {"slug": "deepseek-v4-flash", "name": "DeepSeek V4 Flash", "co": 6, "switched_from": 1, "switched_to": 1}, {"slug": "antigravity", "name": "Antigravity", "co": 9, "switched_from": 0, "switched_to": 0}, {"slug": "gpt-5", "name": "GPT-5", "co": 7, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 793034688, "item_id": 49564668, "url": "https://news.ycombinator.com/item?id=49564668", "by": "bitexploder", "date": "2026-09-04", "stance": "recommend", "quote": "with some prompt taming it is great", "excerpt": "I have a few attention and finish mechanisms in my prompts. I have been using it for a week and a half and with some prompt taming it is great. (I have early access to the models cause I work at the place that makes the model). None of my attempts to ever tame Opus 5 have worked.", "context": "works at the company that makes the model", "use_case": "daily driver model", "switched_from": "", "story": "GPT-6 Astra"}], "threads": [{"url": "https://news.ycombinator.com/item?id=49289112", "title": "Gemini 3.7 Flash", "mentions": 10}, {"url": "https://news.ycombinator.com/item?id=49537553", "title": "Gemini 3.8 Flash and 3.8 Flash Cyber", "mentions": 9}, {"url": "https://news.ycombinator.com/item?id=49913571", "title": "Gemini 4 Argon", "mentions": 6}, {"url": "https://news.ycombinator.com/item?id=50288019", "title": "Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=50073879", "title": "Gemini 4 Argon", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=49672966", "title": "Ask HN: What default model do you use and why?", "mentions": 3}], "sentiment_by_month": {"2025-11": {}, "2025-12": {"recommend": 4, "neutral": 2}, "2026-01": {"recommend": 4, "warn": 1, "compare": 1, "neutral": 1}, "2026-02": {"recommend": 4, "neutral": 3, "warn": 3}, "2026-03": {"warn": 2, "neutral": 2, "recommend": 1}, "2026-04": {"recommend": 5, "warn": 1}, "2026-05": {"warn": 1, "neutral": 2, "compare": 2}, "2026-06": {"neutral": 5, "compare": 2, "warn": 1, "recommend": 3}, "2026-07": {"recommend": 9, "neutral": 1, "warn": 3}, "2026-08": {"recommend": 12, "warn": 3, "neutral": 2}, "2026-09": {"recommend": 20, "compare": 3, "neutral": 7}, "2026-10": {"recommend": 9, "compare": 2, "neutral": 4, "warn": 2}}, "quotes": [{"id": 804750320, "item_id": 50296895, "url": "https://news.ycombinator.com/item?id=50296895", "by": "conception", "date": "2026-10-29", "stance": "recommend", "quote": "Gemini flash 3.8 is an exceptional model and is the bulk of my agentic use", "excerpt": "I love this never-ending people having vastly different experiences situation with LLMs. In my experience, Gemini flash 3.8 is an exceptional model and is the bulk of my agentic use as someone who bounces around models as soon as they come out. I would say it\u2019s the best flash model until 1017 came out. It might still be better than 1017.", "context": "bounces around models as soon as they come out", "use_case": "agentic use", "switched_from": "", "story": "Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5"}, {"id": 804720448, "item_id": 50295028, "url": "https://news.ycombinator.com/item?id=50295028", "by": "2upmedia", "date": "2026-10-29", "stance": "compare", "quote": "a full analysis of Gemini 3.8 Flash vs Gemini 3.5 Flash lite using agentic video understanding", "excerpt": "For some time I've been interested in analyzing videos. Here's a full analysis of Gemini 3.8 Flash vs Gemini 3.5 Flash lite using agentic video understanding and how you could take advantage of both. I also created an open source Claude Code and Codex plugin you could use https://github.com/jorgecolonconsulting/clipwitness.", "context": "", "use_case": "agentic video analysis", "switched_from": "", "story": "Different Gemini model setups for agentic video analysis: Deep vs. Lite"}, {"id": 804705249, "item_id": 50294078, "url": "https://news.ycombinator.com/item?id=50294078", "by": "Revanche1367", "date": "2026-10-29", "stance": "recommend", "quote": "I've gotten good mileage out of 3.8 flash while keeping in mind that it's far from perfect.", "excerpt": "I had been on the pro plan for a few months and recently upgraded to the $200.00 AI Ultra plan because I've gotten good mileage out of 3.8 flash while keeping in mind that it's far from perfect. Argon is better in my experience in terms of reliability (especially in not claiming to have done things it clearly didn't) but I have to agree with the hallucination part, for a \"SOTA\" model (before Carbon came out at least)", "context": "AI Ultra plan subscriber", "use_case": "general AI tasks", "switched_from": "", "story": "Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5"}, {"id": 804621441, "item_id": 50288840, "url": "https://news.ycombinator.com/item?id=50288840", "by": "pcwelder", "date": "2026-10-29", "stance": "recommend", "quote": "Gemini 2.5 flash and 3 flash were highly underrated models that performed way better than the peers", "excerpt": "Gemini 2.5 flash and 3 flash were highly underrated models that performed way better than the peers and we used the hell out of them. Since then none of the Google models have competed well with the others at their price points. Long context performance drop, instruction following issues, unnecessarily complex and sloppish outputs. Argon is no different, it feels just an iteration better than 3.8 flash. I don't trust", "context": "", "use_case": "production LLM workloads", "switched_from": "", "story": "Gemini 4 Carbon is the new #1 on the Artificial Analysis Intelligence Index v5"}, {"id": 804451456, "item_id": 50278216, "url": "https://news.ycombinator.com/item?id=50278216", "by": "mattlondon", "date": "2026-10-28", "stance": "recommend", "quote": "3.8 Flash has been my favourite model and daily driver for a little while now.", "excerpt": "Agreed. I was really looking forward to 4 Flash. 3.8 Flash has been my favourite model and daily driver for a little while now. But to be honest I am now not sure if Argon was the flash model and this Carbon is pro? It's very confusing.", "context": "", "use_case": "everyday use", "switched_from": "", "story": "Gemini 4 Carbon"}, {"id": 803856464, "item_id": 50241029, "url": "https://news.ycombinator.com/item?id=50241029", "by": "jaccola", "date": "2026-10-26", "stance": "warn", "quote": "I love 3.8 Flash, if only it weren\u2019t unusably flaky.", "excerpt": "I love 3.8 Flash, if only it weren\u2019t unusably flaky. Sometimes simple responses take minutes or I get rate limited after sending a single message (I guess it\u2019s a shared pool rate limit). Have you not experienced this (would love to know if there\u2019s a way to actually use it reliably!)", "context": "", "use_case": "coding", "switched_from": "", "story": "IBM CEO says open weight models are now good and cheap on-prem"}, {"id": 803853441, "item_id": 50240840, "url": "https://news.ycombinator.com/item?id=50240840", "by": "mattlondon", "date": "2026-10-26", "stance": "recommend", "quote": "I use Gemini 3.8 Flash as my daily driver for most coding.", "excerpt": "I think, despite the desperate attempt at IBM to remain relevant (and in business), their CEO has a point here that do you really need SOTA models for everything? I had a really nice time with GLM5.2 for a month or two - it was, in my experience, approx Opus 4.5ish level of capability when I think Opus 4.8 was the new hotness Even today, I use Gemini 3.8 Flash as my daily driver for most coding. Its fast and good, ev", "context": "", "use_case": "daily coding", "switched_from": "", "story": "IBM CEO says open weight models are now good and cheap on-prem"}, {"id": 803494436, "item_id": 50218402, "url": "https://news.ycombinator.com/item?id=50218402", "by": "sail0rm00n", "date": "2026-10-24", "stance": "recommend", "quote": "Gemini Flash 3.8, DeepSeek Flash, and Luna are still up there as favorites", "excerpt": "As tribute, I bit the bullet on the $40 plan to test out K3.1 Pro. Still burning through the 5-hour rate limit way too quickly, though. Output quality seems solid enough, but the value will probably make a lot more sense via API pricing for smaller projects. My current tier list based on what I\u2019ve been testing: 1. Opus 5.5 2. Astra 3. Argon 4. Kimi K3.1 Pro (For lightweight/daily driver tasks, Gemini Flash 3.8, DeepS", "context": "", "use_case": "lightweight daily tasks", "switched_from": "", "story": "Kimi K3.1 Pro and K3.1 Pro Highspeed"}, {"id": 801250881, "item_id": 50078180, "url": "https://news.ycombinator.com/item?id=50078180", "by": "mattlondon", "date": "2026-10-13", "stance": "recommend", "quote": "Gemini 3.8 Flash has been a joy to use in comparison (and so fast!) as a daily driver.", "excerpt": "Agree I do not like the way Opus 5.5 communicates with me. It feels like it is trying to act superior in a condescending way. DO NOT LIKE. I have not used Argon yet but Gemini 3.8 Flash has been a joy to use in comparison (and so fast!) as a daily driver.", "context": "", "use_case": "daily driver model", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 801194497, "item_id": 50074656, "url": "https://news.ycombinator.com/item?id=50074656", "by": "eluusive", "date": "2026-10-13", "stance": "warn", "quote": "Almost everything had been stubbed out by 3.8, and none of it was properly integrated into the codebase.", "excerpt": "Just switched, and it seems to be much better. I'm hoping it stops lying. I have Pro max subs for Claude, Codex, Grok, and Google AI... I was forced into using Google by running out of credits elsewhere. I have found that Gemini often claims it did something, but didn't actually complete the task. I just had 3.8 Flash do a major refactor -- that never should have needed to be done in the first place -- and switched t", "context": "has Pro max subs for Claude, Codex, Grok, and Google AI", "use_case": "code refactoring", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 801191905, "item_id": 50074494, "url": "https://news.ycombinator.com/item?id=50074494", "by": "freakynit", "date": "2026-10-13", "stance": "neutral", "quote": "Switched to gemini-3.8-flash in same session... worked.", "excerpt": "Im on pro, installed gemini app, tried argon 4, keeps failing with 404, resource now found. Switched to gemini-3.8-flash in same session... worked. It seems to be rolling out gradually.. not available at once to everyone.", "context": "Gemini Pro subscriber", "use_case": "Gemini app", "switched_from": "Gemini 4 Argon", "story": "Gemini 4 Argon"}, {"id": 801003824, "item_id": 50062739, "url": "https://news.ycombinator.com/item?id=50062739", "by": "mattlondon", "date": "2026-10-12", "stance": "recommend", "quote": "prefer Gemini 3.8 flash as a daily driver just because it's so much more pleasant (and faster!) to work with", "excerpt": "Gemini 4 Argon release a few days ago was frontier a few days ago. Things move fast. I think some of the benchmarks that Meta didn't pick show Gemini 4 Argon ahead but really the benchmarks are not that great any more and getting increasingly disconnected from reality as people search for \"headroom\" in the evals to avoid saturation I think. Opus 5.5 is \"top\" for example but I really dislike the way it talks to me (it", "context": "", "use_case": "daily driver, coding", "switched_from": "", "story": "Muse Wonder"}, {"id": 800792739, "item_id": 50049546, "url": "https://news.ycombinator.com/item?id=50049546", "by": "joaoviniciusgs", "date": "2026-10-12", "stance": "neutral", "quote": "It's honestly not as bad as it sounds.", "excerpt": "So yeah, I made a clone of Boom 3D. If you don't know what Boom 3D is, it's an audio enhancement app available on Steam and other stores that makes your headphones sound more immersive with 3D spatial audio and other audio effects. It's called OpenBoom, and it's an open-source alternative for Windows built with Rust and Tauri. It aims to bring features like 3D spatial audio, a 31-band equalizer, AutoEq headphone prof", "context": "", "use_case": "building the app", "switched_from": "", "story": "I made an open-source Boom 3D clone. Wanna check it out?"}, {"id": 800299664, "item_id": 50018729, "url": "https://news.ycombinator.com/item?id=50018729", "by": "dada216", "date": "2026-10-09", "stance": "recommend", "quote": "for what amounts to a web search Gemini 3.8 flash is better than the big models", "excerpt": "I even find that for what amounts to a web search Gemini 3.8 flash is better than the big models, stuff like the links to updated tax codes in different countries, or whatever MS is doing with Azure/o365 or AWS with their plethora of products. I think use cases are the real reason why people have such different experiences, I too find that Opus5.5/Astra/6 are better for UI/UX now, it wasn't the case a year ago, at so", "context": "", "use_case": "web search style queries", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 800206721, "item_id": 50012920, "url": "https://news.ycombinator.com/item?id=50012920", "by": "robertlane0", "date": "2026-10-08", "stance": "neutral", "quote": "Gemini 3.8 Flash, which has been my benchline for \"cheap and smart enough\"", "excerpt": "Well, according to Artificial Analysis (which I'll admit I've been using as a bit of a mental crutch to avoid comparing models myself, so YMMV), it's smarter and slightly cheaper than Gemini 3.8 Flash, which has been my benchline for \"cheap and smart enough\", I'll give it a try on OpenCode for the week but I'm not sure I'll be compelled enough to switch from Muse Spark 1.3.", "context": "", "use_case": "baseline cheap model", "switched_from": "", "story": "Step 5 Preview, a 1M-context MoE from StepFun, shows up on OpenRouter"}, {"id": 799372465, "item_id": 49960779, "url": "https://news.ycombinator.com/item?id=49960779", "by": "kaydub", "date": "2026-10-05", "stance": "neutral", "quote": "For personal projects I bounce between Sol/Terra and Gemini Flash.", "excerpt": "Nope. Opus and Sol for the most part. Haven't even used Astra or Fable. At work it's all Anthropic. I spent a while on Sonnet models but have been pretty consistent about using Opus now. For personal projects I bounce between Sol/Terra and Gemini Flash. Most of the models are good enough now. You don't need all these documents, memory, plugins, skills, etc. MCPs are good for hooking up to external sources of data (at", "context": "", "use_case": "personal projects", "switched_from": "", "story": "Agents don't need memory, they need documentation"}, {"id": 799288465, "item_id": 49955529, "url": "https://news.ycombinator.com/item?id=49955529", "by": "a11r", "date": "2026-10-04", "stance": "compare", "quote": "FlashNext is also better at finding issues in generated code than Gemini 3.8 Flash.", "excerpt": "We recently moved from 27B to Flash Next. The quality is superior for coding. Our workload is primarily well-defined coding tasks that need to be attempted a few times before the model gets it just right. FlashNext is also better at finding issues in generated code than Gemini 3.8 Flash.", "context": "", "use_case": "finding issues in generated code", "switched_from": "", "story": "Run Qwen 3.8 Flash Next (125B) on consumer hardware (RTX 4090) at 100T/s"}, {"id": 799112145, "item_id": 49944509, "url": "https://news.ycombinator.com/item?id=49944509", "by": "solnyshok", "date": "2026-10-03", "stance": "recommend", "quote": "google flash was good for topic research and general queries", "excerpt": "what free tier models are still available comparable to flash? I use claude for IT stuff, but google flash was good for topic research and general queries, with some basic linux administration advise.I can run moe up to 48gb on my own hardware too, if needed.", "context": "", "use_case": "topic research, general queries", "switched_from": "", "story": "Gemini ending free use of Flash and Pro models"}, {"id": 798785952, "item_id": 49924122, "url": "https://news.ycombinator.com/item?id=49924122", "by": "LarsDu88", "date": "2026-10-01", "stance": "recommend", "quote": "I use Gemini Flash every single day without paying a dime.", "excerpt": "That's one interpretation, but I think people are simply having amnesia of the past 2 years. The better interpretation is Google completely commoditized and killed ChatGPT's initial chat product. If you think about it, Google right now has Gemini Flash running on single TPU instances at massive scale serving almost every android device. I use it every day and it's more capable than GPT-40. This literally forced Anthr", "context": "", "use_case": "daily LLM calls", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 798687056, "item_id": 49917941, "url": "https://news.ycombinator.com/item?id=49917941", "by": "lp92", "date": "2026-10-01", "stance": "recommend", "quote": "3.8 Flash does really well for writing code as long as you give it a good design and plan to follow.", "excerpt": "Same! 3.8 Flash does really well for writing code as long as you give it a good design and plan to follow. I use Opus for architecture/design/implementation plans and let Gemini 3.8 work using those. Even on the $20 Pro plan I've only come down to 10% before the weekly reset.", "context": "on the $20 Pro plan", "use_case": "implementing code from plans", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 798646784, "item_id": 49915424, "url": "https://news.ycombinator.com/item?id=49915424", "by": "gcy", "date": "2026-09-30", "stance": "recommend", "quote": "it's fast and almost free (sufficient quota with pro account)", "excerpt": "I use 3.8 Flash for daily troubleshooting tasks e.g. help me find out why certain app crashes or certain website does not load normally with playwright-cli. Sure it's not as capable but it's fast and almost free (sufficient quota with pro account). The only thing that bugs me is that I need to use `--dangerously-skip-permissions` as it does not have auto review.", "context": "", "use_case": "daily troubleshooting", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 798645042, "item_id": 49915315, "url": "https://news.ycombinator.com/item?id=49915315", "by": "huydotnet", "date": "2026-09-30", "stance": "recommend", "quote": "If there's already a detailed plan, 3.7 can complete the task much faster.", "excerpt": "I recently subscribed to Claude, and was very unhappy about the usage limit of the $20 pro plan. Then I found a trick, since I got free Google AI Pro via my phone carrier, I use Opus 5.5 High for planning, and then dispatching agy to do works. Most of the time 3.8 works fine, but it's a bit slow if compare to 3.7 Flash. If there's already a detailed plan, 3.7 can complete the task much faster. And the best thing abou", "context": "", "use_case": "executing detailed plans", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 798636400, "item_id": 49914775, "url": "https://news.ycombinator.com/item?id=49914775", "by": "p_l", "date": "2026-09-30", "stance": "neutral", "quote": "pretty much it switched to latest Flash series as main option", "excerpt": "Not sure what's the problem with phone app rollout, mine has 3.1 Pro, 3.5 Flash-Lite, and 3.8 Flash (with optional extra effort), and pretty much it switched to latest Flash series as main option since 3.5 just after release", "context": "", "use_case": "phone app model", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 798621664, "item_id": 49913854, "url": "https://news.ycombinator.com/item?id=49913854", "by": "spankalee", "date": "2026-09-30", "stance": "recommend", "quote": "3.8 Flash is just quite good", "excerpt": "3.8 Flash is just quite good, and so is the Antigravity harness. I use a mix of Fable 5.1, Opus 5.5, and Gemini 3.8 Flash and Gemini holds it's own. Especially in writing, frontend, and sysadmin work. agy for configuring a NixOS system has been truly incredible.", "context": "", "use_case": "writing, frontend, sysadmin", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 798532000, "item_id": 49908250, "url": "https://news.ycombinator.com/item?id=49908250", "by": "lp92", "date": "2026-09-30", "stance": "recommend", "quote": "Currently I'm building my own generative modeling + aero sim package largely using Gemini and it's been working great.", "excerpt": "Since Gemini 3.8 Flash release, I've been largely using that for my coding ttasks. The architectureand design work I use Opus, but the rest of the work is done via Gemini 3.8. I don'thave to worry aboutweekly limits even on the $20 plan. I get down to about 10% weekly limit before it resets. Currently I'm building my own generative modeling + aero sim package largely using Gemini and it's been working great.", "context": "building a generative modeling and aero sim package", "use_case": "most coding tasks", "switched_from": "", "story": "GPT-6.1 Sol replaces GPT-6 Sol after just 7 days, with near-Astra intelligence"}, {"id": 798531696, "item_id": 49908231, "url": "https://news.ycombinator.com/item?id=49908231", "by": "lumzell", "date": "2026-09-30", "stance": "neutral", "quote": "I tested it on my own code review set with Gemini Flash.", "excerpt": "In my case it actually made a difference. I tested it on my own code review set with Gemini Flash. On low it found fewer bugs than on default around 90% versus 97% but was about three times faster and a lot cheaper. On high it actually found everything in the hardest case but took almost three minutes per call. so I think the difference is real you only see it if you run the same fixed cases a few times and not by fe", "context": "", "use_case": "code review bug finding", "switched_from": "", "story": "GPT-6.1 Sol replaces GPT-6 Sol after just 7 days, with near-Astra intelligence"}, {"id": 798030417, "item_id": 49876901, "url": "https://news.ycombinator.com/item?id=49876901", "by": "slipwalker", "date": "2026-09-28", "stance": "neutral", "quote": "gemini-3.6-flash for brainstorming problems", "excerpt": "mostly GLM-5-turbo for coding, and gemini-3.6-flash for brainstorming problems ( why ? token cost and availability at work )", "context": "", "use_case": "brainstorming", "switched_from": "", "story": "Ask HN: Which model do you use for work?"}, {"id": 796666672, "item_id": 49791667, "url": "https://news.ycombinator.com/item?id=49791667", "by": "haellsigh", "date": "2026-09-21", "stance": "recommend", "quote": "They really redeemed themselves with the 3.5 Flash series, it's great. I love how fast it is.", "excerpt": "I remember the Gemini 2.5 Pro series was the best at text, but failed half of it's tool calls. They really redeemed themselves with the 3.5 Flash series, it's great. I love how fast it is. Now if only they could offer a subscription service for it...", "context": "", "use_case": "tool calling", "switched_from": "", "story": "Grok 4.7"}, {"id": 796659841, "item_id": 49791240, "url": "https://news.ycombinator.com/item?id=49791240", "by": "moojacob", "date": "2026-09-21", "stance": "neutral", "quote": "I'll have to try Gemini Flash for coding.", "excerpt": "I'll have to try Gemini Flash for coding. The reason I haven't I used Gemini for coding is last time I tried it couldn't call tools very well. I am a huge fan of Gemini Pro for chat... gemini somehow just knows the most obscure stuff. I'll double check something Gemini said and find the source is deep inside a hard to access scientific paper. Google just has the best index of the internet.", "context": "", "use_case": "coding", "switched_from": "", "story": "Grok 4.7"}, {"id": 795788465, "item_id": 49736779, "url": "https://news.ycombinator.com/item?id=49736779", "by": "akiselev", "date": "2026-09-17", "stance": "neutral", "quote": "It just sends the PDF to Gemini Flash and asks it to extract semi structured data", "excerpt": "Shameless plug for the slop coded CLI I use in my workflow: https://github.com/akiselev/datasheet-cli It just sends the PDF to Gemini Flash and asks it to extract semi structured data (semi structured in the sense that it's not fully structured extraction, but its a JSON file to feed into the next step of the LLM design process). Works pretty well in general, though I should update to the latest Gemini version.", "context": "", "use_case": "PDF data extraction", "switched_from": "", "story": "This PCB is brought to you by Fable 5"}, {"id": 795571712, "item_id": 49723232, "url": "https://news.ycombinator.com/item?id=49723232", "by": "TomGarden", "date": "2026-09-16", "stance": "recommend", "quote": "3.8 flash is the best back-and-forth model for iterating imo", "excerpt": "I love it as a variation from the others. 3.8 flash is the best back-and-forth model for iterating imo, but would not use for long horizon", "context": "", "use_case": "iterating back-and-forth", "switched_from": "", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 795165632, "item_id": 49697852, "url": "https://news.ycombinator.com/item?id=49697852", "by": "ipsod", "date": "2026-09-14", "stance": "recommend", "quote": "It's ridiculously fast, and generally very good with real-world knowledge.", "excerpt": "It's ridiculously fast, and generally very good with real-world knowledge. It's my go-to for anything non-coding, and for quick fixes/questions/prototypes. If metrics measured what most people need from an LLM, it's competitive, IMO, and with their TPU chips, it's probably economically competitive.", "context": "", "use_case": "non-coding questions, quick prototypes", "switched_from": "", "story": "Why is Google still serving dodgy ads?"}, {"id": 794843024, "item_id": 49677689, "url": "https://news.ycombinator.com/item?id=49677689", "by": "tucnak", "date": "2026-09-12", "stance": "recommend", "quote": "I use 3.8 flash in Antigravity a lot, and thoroughly prefer it to most Pro-class models.", "excerpt": "Hard disagree. I use 3.8 flash in Antigravity a lot, and thoroughly prefer it to most Pro-class models. It's really fast, and I've had it make crazy progress on compiler-like problems that previous models including Opus simply failed at. On ultra plan you can have it going for hours, and make incremental progress with good prompting for review interrupts. It solved a problem I couldn't solve for weeks in under 6 hour", "context": "", "use_case": "compiler-like coding problems", "switched_from": "", "story": "Real-SWE: Benchmarking AI models on private, real-world, enterprise codebases"}, {"id": 794804993, "item_id": 49675312, "url": "https://news.ycombinator.com/item?id=49675312", "by": "gtadesktop1", "date": "2026-09-12", "stance": "recommend", "quote": "You can use Gemini 3.8 Flash and you can give him system instructions.", "excerpt": "I used Claude too, but I was banned so I searched for new like you yet and found Google AI Studio. It has a Playground-Mode for the newest models you usually have to pay but in the Playground-Mode you don't pay one cent. You can use Gemini 3.8 Flash and you can give him system instructions. For example you can say \"You're a AI Agent that helps me with my mobile app\" and he helps you with your mobile app. It has a con", "context": "", "use_case": "mobile app help", "switched_from": "Claude", "story": "Ask HN: What default model do you use and why?"}, {"id": 794786598, "item_id": 49674162, "url": "https://news.ycombinator.com/item?id=49674162", "by": "jamesponddotco", "date": "2026-09-12", "stance": "neutral", "quote": "Gemini Flash 3.8 gave me the closest to good writing out of the ones I tested.", "excerpt": "Given that Fable is the only one that fucking listens to me and writes proper Go code, that\u2019s what I use for everything code-related. At least on my personal projects. If I don\u2019t care about the code, i.e. I\u2019m writing something quick just to test something, I\u2019ll use GPT Astra to save my Fable tokens. For conversations and research I usually go with GPT Astra Pro. For Home Assistant I use a combination of Grok 4.20 and", "context": "", "use_case": "fiction writing ideas", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 794778480, "item_id": 49673655, "url": "https://news.ycombinator.com/item?id=49673655", "by": "seanmcdirmid", "date": "2026-09-12", "stance": "recommend", "quote": "Gemini 3.8 flash via Antigravity desktop has been my daily driver for the last few weeks.", "excerpt": "Gemini 3.8 flash via Antigravity desktop has been my daily driver for the last few weeks. I also use DeepSeek V4 flash and a Qwen 3.6 MoE for local stuff.", "context": "", "use_case": "daily driver", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 794108288, "item_id": 49631768, "url": "https://news.ycombinator.com/item?id=49631768", "by": "toshvelaga", "date": "2026-09-09", "stance": "recommend", "quote": "Gemini 3.8 flash and gemini 3.1 pro seem to lead across the other LLMs.", "excerpt": "There are no sites like artificialanalysis.ai or arena.ai for healthcare benchmarks so I decided to build it. I ran the leading models from openai, anthropic, and google on MedXpertQA: https://github.com/TsinghuaC3I/MedXpertQA#leaderboard The results show scores across organ systems and across diagnosis, treatment, and basic science. Gemini 3.8 flash and gemini 3.1 pro seem to lead across the other LLMs. The last tim", "context": "built a healthcare LLM benchmark", "use_case": "medical question benchmark", "switched_from": "", "story": "Benchmarked how the latest LLMs perform on expert level medical questions"}, {"id": 793915104, "item_id": 49619694, "url": "https://news.ycombinator.com/item?id=49619694", "by": "artdigital", "date": "2026-09-09", "stance": "recommend", "quote": "Gemini Flash 3.8 is an awesome model! I use it all the time", "excerpt": "More because Spark is not good. Gemini Flash 3.8 is an awesome model! I use it all the time Spark asks you for every single tool call, often forgets earlier parts of the conversation, is unable to use apps unless you explicitly tag them and and and Google has great models, but their harnesses and products are just bad", "context": "", "use_case": "general AI model use", "switched_from": "", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 793861618, "item_id": 49616351, "url": "https://news.ycombinator.com/item?id=49616351", "by": "bel8", "date": "2026-09-08", "stance": "compare", "quote": "the only faster acessible model currently is Gemini 3.8 Flash which is around 250-280 tok/s", "excerpt": "I think they had this sitting idle for a while, waiting for their AI division to deliver a capable LLM to power it. Now they have Muse Spark 1.3, which is somewhere between Sonnet and Flable (Opus tier in my experience) in intelligence, but is very fast at 200+ tok/s. I have been using Muse Spark 1.3 contrib (the one that shares your data for training but is much cheaper) via OpenCode Go $10/mo plan for coding and th", "context": "", "use_case": "", "switched_from": "", "story": "Muse \u2013 Meta\u2019s personal AI agent"}, {"id": 793765617, "item_id": 49610351, "url": "https://news.ycombinator.com/item?id=49610351", "by": "hakunin", "date": "2026-09-08", "stance": "recommend", "quote": "then switched to Gemini Flash for the same price inline, or half price using batch API, and the difference is night and day.", "excerpt": "I've made a personal doc tool based on Mistral OCR API at first, and then switched to Gemini Flash for the same price inline, or half price using batch API, and the difference is night and day. Mistral doesn't even come close on anything non-trivial. Longer story here: https://max.engineer/ringbinder", "context": "built a personal doc tool", "use_case": "document OCR", "switched_from": "Mistral OCR", "story": "Mistral raises \u20ac3B"}, {"id": 792976864, "item_id": 49561054, "url": "https://news.ycombinator.com/item?id=49561054", "by": "conception", "date": "2026-09-04", "stance": "recommend", "quote": "Flash 3.8 is rad. Easily my daily driver now.", "excerpt": "Flash 3.8 is rad. Easily my daily driver now. Only downside is it's Gemini so sometimes it just keeps going until it wants to be done.", "context": "", "use_case": "daily driver model", "switched_from": "", "story": "GPT-6 Astra"}, {"id": 792613152, "item_id": 49538322, "url": "https://news.ycombinator.com/item?id=49538322", "by": "datlife", "date": "2026-09-02", "stance": "recommend", "quote": "I use Flash model as code implementation executor, then have GPT-5.6-Sol or Opus to review the work.", "excerpt": "I use Flash model as code implementation executor, then have GPT-5.6-Sol or Opus to review the work. Pretty good so far and presumably less expensive.", "context": "", "use_case": "code implementation", "switched_from": "", "story": "Gemini 3.8 Flash and 3.8 Flash Cyber"}, {"id": 790646353, "item_id": 49415397, "url": "https://news.ycombinator.com/item?id=49415397", "by": "DefamationStati", "date": "2026-08-24", "stance": "warn", "quote": "the limits as absolutely abysmal when using 3.7 flash in antigravity", "excerpt": "I've got the AI pro plan for Gemini and the limits as absolutely abysmal when using 3.7 flash in antigravity, If I use swarms then I can't even finish a single prompt without it reaching the limit.", "context": "has Gemini AI Pro plan", "use_case": "AI coding", "switched_from": "", "story": "Anthropic's best AI model struggles to attract users as cheaper tools thrive"}, {"id": 788636224, "item_id": 49289764, "url": "https://news.ycombinator.com/item?id=49289764", "by": "UncleOxidant", "date": "2026-08-13", "stance": "recommend", "quote": "Yes, 3.6 Flash is very fast.", "excerpt": "Yes, 3.6 Flash is very fast. I used to get a fair amount of usage of the Gemini Flash models on the free tier. I signed up for their $4.99/month tier (includes 400GB of Google space which was also enticing) and it turns out I only get about 15 to 20 minutes of usage before I get a come-back-in-7-days message. Comically low usage limits on that plan.", "context": "", "use_case": "general use", "switched_from": "", "story": "Gemini 3.7 Flash"}, {"id": 788628736, "item_id": 49289296, "url": "https://news.ycombinator.com/item?id=49289296", "by": "fmind-dev", "date": "2026-08-13", "stance": "recommend", "quote": "Gemini Flash is one of the best \"good-enough\" models.", "excerpt": "Gemini Flash is one of the best \"good-enough\" models. I use this type of model daily, for automation and quick development iteration loops. Unfortunately, it's often not strong enough for heavy refactoring and long running development loops.", "context": "", "use_case": "automation and quick dev iteration loops", "switched_from": "", "story": "Gemini 3.7 Flash"}, {"id": 788324113, "item_id": 49270257, "url": "https://news.ycombinator.com/item?id=49270257", "by": "antonvs", "date": "2026-08-12", "stance": "recommend", "quote": "It\u2019s very competent, and quite a bit cheaper than Claude.", "excerpt": "How are you accessing it? You may be using one of the limited models. I use Gemini Antigravity daily for software design and coding, mostly using the Gemini 3.5 Flash model. It\u2019s very competent, and quite a bit cheaper than Claude.", "context": "", "use_case": "software design and coding", "switched_from": "", "story": "Gemini becomes Google's fastest-growing product ever as it hits 1B users"}, {"id": 783097250, "item_id": 48943578, "url": "https://news.ycombinator.com/item?id=48943578", "by": "arman-w-jalili", "date": "2026-07-16", "stance": "warn", "quote": "i casually get error, api not available, especially gemeni-flash", "excerpt": "at the moment private i use mainly deepseek, about 80% and very very happy with it, at work we have copilot, i'm not sure, but the quality of service has got degraded in my opinion, speed is very low, i casually get error, api not available, especially gemeni-flash ,i have the feeling GPT5.4 is not as good as before, and with serious work i burn all my 400\u20ac budget in 4 days", "context": "", "use_case": "work LLM via Copilot", "switched_from": "", "story": "What % of your usage is open source vs. frontier models?"}]}