{"slug": "google-ai-studio", "name": "Google AI Studio", "category": "ai", "category_name": "AI models and assistants", "description": "Google's web workspace for prototyping with Gemini models and generating Gemini API keys.", "recommenders": 5, "commenters": 20, "warners": 6, "score": 1.129, "rising": 3.67, "first": "2025-11-18", "latest": "2026-10-29", "why": "HN commenters like it as a free way to use Gemini models, with fast API key setup and a 1-million-token context window.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 5, "neutral": 6, "compare": 3, "warn": 7}, "spark": [0, 0, 0, 0, 0, 0, 0, 1, 0, 2, 2, 0], "listed": true, "loved": ["Free access", "App prototyping"], "caveat": "Confusing UX", "short_quote": "consider it the most dead simple/fastest dev dashboard to get started compared to the others like OpenAI/Anthropic", "icon": true, "domain": null, "github_repo": null, "official_url": "https://aistudio.google.com/", "pricing": "freemium", "aliases": ["Google AI Studio", "AI Studio"], "verdict": [{"text": "HN commenters like it as a free way to use Gemini models,", "cites": [{"id": 794804992, "item_id": 49675312, "url": "https://news.ycombinator.com/item?id=49675312", "by": "gtadesktop1", "date": "2026-09-12", "stance": "recommend", "quote": "in the Playground-Mode you don't pay one cent", "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": "banned from Claude", "use_case": "free LLM access for app development", "switched_from": "Claude", "story": "Ask HN: What default model do you use and why?"}, {"id": 788638912, "item_id": 49289932, "url": "https://news.ycombinator.com/item?id=49289932", "by": "axus", "date": "2026-08-13", "stance": "recommend", "quote": "It's on Google AI Studio, which I use for free when I'm not on computers I control.", "excerpt": "It's on Google AI Studio, which I use for free when I'm not on computers I control. It did fine on my usual benchmark about configuring old Sparc hardware, maybe output slightly faster than before. Even included something new to check in the firmware.", "context": "", "use_case": "free model access", "switched_from": "", "story": "Gemini 3.7 Flash"}]}, {"text": " with fast API key setup and a 1-million-token context window.", "cites": [{"id": 788658496, "item_id": 49291156, "url": "https://news.ycombinator.com/item?id=49291156", "by": "qlte", "date": "2026-08-13", "stance": "recommend", "quote": "consider it the most dead simple/fastest dev dashboard to get started compared to the others like OpenAI/Anthropic", "excerpt": "I didn't have that issue back when I originally created my API keys a couple years ago. Just out of curiosity I switched to a different Google account that had never interacted with AI Studio and never used Google Cloud console. It was literally two clicks, and didn't even leave the page: the dialog asked to create a project and type in a name, I did that, clicked submit and then it was selected as the default projec", "context": "", "use_case": "Gemini API keys", "switched_from": "", "story": "Gemini 3.7 Flash"}, {"id": 794804992, "item_id": 49675312, "url": "https://news.ycombinator.com/item?id=49675312", "by": "gtadesktop1", "date": "2026-09-12", "stance": "recommend", "quote": "in the Playground-Mode you don't pay one cent", "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": "banned from Claude", "use_case": "free LLM access for app development", "switched_from": "Claude", "story": "Ask HN: What default model do you use and why?"}]}, {"text": " The most common complaint is a confusing UI,", "cites": [{"id": 798622144, "item_id": 49913884, "url": "https://news.ycombinator.com/item?id=49913884", "by": "deanc", "date": "2026-09-30", "stance": "warn", "quote": "I don't _want_ to use aistudio. The UX is confusing", "excerpt": "At this point I just think they are benchmaxxing and all talk and no action. I pay for AI plus because I wanted more storage, and when I go to gemini.google.com the most recent model I can use is 3.6-flash-lite. Two revisions have been released since then and they still can't put these things in the hands of customers. Why is it that other providers can get the models into the hands of customers right away? Google is", "context": "", "use_case": "", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 772409489, "item_id": 48275593, "url": "https://news.ycombinator.com/item?id=48275593", "by": "cafkafk", "date": "2026-05-25", "stance": "compare", "quote": "Google Vertex (or Google AI Studio) might be a potential alternative, but the UX is a lot worse", "excerpt": "Google Vertex (or Google AI Studio) might be a potential alternative, but the UX is a lot worse, and it can be hard to estimate cost since it's typically lagging. One of the advantages you'll miss when moving from openrouter is going from a \"debit\" based system to a \"credit\" based one. I.e. openrouter you pay up front, Google you're billed monthly based on usage.", "context": "", "use_case": "LLM API access", "switched_from": "", "story": "Ask HN: Some Sensible Alternative to Openrouter?"}, {"id": 735488880, "item_id": 45968055, "url": "https://news.ycombinator.com/item?id=45968055", "by": "Der_Einzige", "date": "2025-11-18", "stance": "compare", "quote": "I love the google AI studio, but I hate it too for not enabling a whole host of advanced features.", "excerpt": "When will they allow us to use modern LLM samplers like min_p, or even better samplers like top N sigma, or P-less decoding? They are provably SOTA and in some cases enable infinite temperature. Temperature continues to be gated to maximum of 0.2, and there's still the hidden top_k of 64 that you can't turn off. I love the google AI studio, but I hate it too for not enabling a whole host of advanced features. So many", "context": "", "use_case": "LLM prompting", "switched_from": "", "story": "Gemini 3"}]}, {"text": " with further warnings about hard-to-predict costs and reports that deleted chats persist on the server.", "cites": [{"id": 783013795, "item_id": 48938362, "url": "https://news.ycombinator.com/item?id=48938362", "by": "jdw64", "date": "2026-07-16", "stance": "warn", "quote": "In AI Studio, they say you have to use the API. You try it and get billed 80$", "excerpt": "I recommend that every AI user start with Gemini as their first AI. Use ChatGPT, and it's ask a question, get an answer, done. Tell it to code, get the code, done. But use Gemini? You get burned by the hallucinations Gemini casually spews out on a daily basis. You develop a habit of fact checking every single answer. You learn that blindly trusting the AI's response will get you absolutely screwed. AI answers must al", "context": "", "use_case": "", "switched_from": "", "story": "Google Gemini Launch Delayed as Tech Falls Short of Internal Goals"}, {"id": 772409489, "item_id": 48275593, "url": "https://news.ycombinator.com/item?id=48275593", "by": "cafkafk", "date": "2026-05-25", "stance": "compare", "quote": "Google Vertex (or Google AI Studio) might be a potential alternative, but the UX is a lot worse", "excerpt": "Google Vertex (or Google AI Studio) might be a potential alternative, but the UX is a lot worse, and it can be hard to estimate cost since it's typically lagging. One of the advantages you'll miss when moving from openrouter is going from a \"debit\" based system to a \"credit\" based one. I.e. openrouter you pay up front, Google you're billed monthly based on usage.", "context": "", "use_case": "LLM API access", "switched_from": "", "story": "Ask HN: Some Sensible Alternative to Openrouter?"}, {"id": 785683152, "item_id": 49105197, "url": "https://news.ycombinator.com/item?id=49105197", "by": "Bitu79", "date": "2026-07-29", "stance": "warn", "quote": "Google AI Studio\u2019s \u201cDelete\u201d button does not delete the server\u2011side chat.", "excerpt": "I found that Google AI Studio\u2019s \u201cDelete\u201d button does not delete the server\u2011side chat. I tested it by deleting a prompt, deleting the JSON file from Drive, and emptying the Trash. The file was fully gone. Then I used Google\u2019s official recovery tool. The JSON came back \u2014 and the model instantly continued the conversation with full context. This is only possible if the server\u2011side session and conversation were never del", "context": "", "use_case": "", "switched_from": "", "story": "Google AI Studio \"Delete\" doesn't delete \u2013 server chat persists (3 videos)"}]}], "praise": [{"label": "Free access", "summary": "Commenters use the playground and free API tier to run recent Gemini models at no cost.", "quotes": [{"id": 794804992, "item_id": 49675312, "url": "https://news.ycombinator.com/item?id=49675312", "by": "gtadesktop1", "date": "2026-09-12", "stance": "recommend", "quote": "in the Playground-Mode you don't pay one cent", "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": "banned from Claude", "use_case": "free LLM access for app development", "switched_from": "Claude", "story": "Ask HN: What default model do you use and why?"}, {"id": 788638912, "item_id": 49289932, "url": "https://news.ycombinator.com/item?id=49289932", "by": "axus", "date": "2026-08-13", "stance": "recommend", "quote": "It's on Google AI Studio, which I use for free when I'm not on computers I control.", "excerpt": "It's on Google AI Studio, which I use for free when I'm not on computers I control. It did fine on my usual benchmark about configuring old Sparc hardware, maybe output slightly faster than before. Even included something new to check in the firmware.", "context": "", "use_case": "free model access", "switched_from": "", "story": "Gemini 3.7 Flash"}, {"id": 788658496, "item_id": 49291156, "url": "https://news.ycombinator.com/item?id=49291156", "by": "qlte", "date": "2026-08-13", "stance": "recommend", "quote": "consider it the most dead simple/fastest dev dashboard to get started compared to the others like OpenAI/Anthropic", "excerpt": "I didn't have that issue back when I originally created my API keys a couple years ago. Just out of curiosity I switched to a different Google account that had never interacted with AI Studio and never used Google Cloud console. It was literally two clicks, and didn't even leave the page: the dialog asked to create a project and type in a name, I did that, clicked submit and then it was selected as the default projec", "context": "", "use_case": "Gemini API keys", "switched_from": "", "story": "Gemini 3.7 Flash"}]}, {"label": "App prototyping", "summary": "Users, including non-programmers, report building websites, front-end designs and Android apps with it.", "quotes": [{"id": 775825648, "item_id": 48489103, "url": "https://news.ycombinator.com/item?id=48489103", "by": "manimonji", "date": "2026-06-11", "stance": "recommend", "quote": "I used google AI studio, and it designed the thing very well", "excerpt": "It's just that when I was exploring different things, I really liked front-end and I put more time on that. Recently I used google AI studio, and it designed the thing very well, and I sucked at designing and slow in developing. In other areas, it helped me a lot, for example Laravel docs looked hard to learn for me and I just used php or node js or Django or whatever to avoid Laravel instead, but then I just wanted ", "context": "", "use_case": "front-end design and prototyping", "switched_from": "", "story": "Why would someone want to learn code when AI does it better and faster?"}, {"id": 744837587, "item_id": 46552349, "url": "https://news.ycombinator.com/item?id=46552349", "by": "stingtao", "date": "2026-01-09", "stance": "neutral", "quote": "I used Cursor / Codex / Claude CLI / AI Studio / Antigravity and made many websites.", "excerpt": "I am not a programmer. I used Cursor / Codex / Claude CLI / AI Studio / Antigravity and made many websites. For me, I get 1000x AI dev since my initial comparison point is very very low. I created: https://live.stingtao.info for me to do interactive live quiz (like Kahoot) https://presentation.stingtao,.info for me to make presentations by AI (like gamma) https://catsbook.stingtao.info for cats to register their own ", "context": "not a programmer", "use_case": "building websites", "switched_from": "", "story": "AI Coding Assistants Are Getting Worse"}, {"id": 773430692, "item_id": 48339418, "url": "https://news.ycombinator.com/item?id=48339418", "by": "bpavuk", "date": "2026-05-30", "stance": "neutral", "quote": "you can vibecode Android apps in Google AI Studio with streaming from a Google-hosted device", "excerpt": "Android native dev here. > What is going on in the world of pure IOS/Android app development? I'll speak only for Android. I am tired of Google breaking source compatibility with every AndroidX release and remaining on outdated IntelliJ Platform versions in Android Studio. not too long ago, Google released AGP 9.0, which was a SHOCKWAVE for many Android projects. many compiler plugins' compatibility, including Google", "context": "Android native dev", "use_case": "vibe coding Android apps", "switched_from": "", "story": "Ask HN: What Is the State of App Development in 2026?"}]}, {"label": "Prompt experimentation", "summary": "Commenters fork chats after successful prompts and adjust settings like temperature to test outputs.", "quotes": [{"id": 794024608, "item_id": 49626538, "url": "https://news.ycombinator.com/item?id=49626538", "by": "dwringer", "date": "2026-09-09", "stance": "recommend", "quote": "I used to use Google's AI Studio a lot and fork it after every successful prompt interaction", "excerpt": "I only made it through the first round of prompt selection; both options for the second step were equally pointless and not at all prompts I would ever expect to result in a constructive outcome. In my experience, telling the model it screwed up without specifically addressing, unambiguously, how to fix it, only leads to more suffering. If this page illustrates nothing else, I think it shows the immense downside of t", "context": "", "use_case": "forking and reverting LLM prompts", "switched_from": "", "story": "Claude, change the \u201cAdd to Cart\u201d button to blue"}, {"id": 753227392, "item_id": 47076712, "url": "https://news.ycombinator.com/item?id=47076712", "by": "benatkin", "date": "2026-02-19", "stance": "neutral", "quote": "I used the AI studio link and tried running it with the temperature set to 1.75", "excerpt": "I used the AI studio link and tried running it with the temperature set to 1.75: https://jsbin.com/locodaqovu/edit?html,output", "context": "", "use_case": "testing Gemini 3.1 Pro", "switched_from": "", "story": "Gemini 3.1 Pro"}]}, {"label": "Quick setup", "summary": "One commenter got a free-tier API key in a few clicks and calls it the simplest dev dashboard.", "quotes": [{"id": 788658496, "item_id": 49291156, "url": "https://news.ycombinator.com/item?id=49291156", "by": "qlte", "date": "2026-08-13", "stance": "recommend", "quote": "consider it the most dead simple/fastest dev dashboard to get started compared to the others like OpenAI/Anthropic", "excerpt": "I didn't have that issue back when I originally created my API keys a couple years ago. Just out of curiosity I switched to a different Google account that had never interacted with AI Studio and never used Google Cloud console. It was literally two clicks, and didn't even leave the page: the dialog asked to create a project and type in a name, I did that, clicked submit and then it was selected as the default projec", "context": "", "use_case": "Gemini API keys", "switched_from": "", "story": "Gemini 3.7 Flash"}]}, {"label": "Long context", "summary": "Commenters cite a context window of up to 1 million tokens.", "quotes": [{"id": 794804992, "item_id": 49675312, "url": "https://news.ycombinator.com/item?id=49675312", "by": "gtadesktop1", "date": "2026-09-12", "stance": "recommend", "quote": "in the Playground-Mode you don't pay one cent", "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": "banned from Claude", "use_case": "free LLM access for app development", "switched_from": "Claude", "story": "Ask HN: What default model do you use and why?"}]}], "caveats": [{"label": "Confusing UX", "summary": "Several commenters find the interface confusing or frustrating, including disappearing update banners.", "quotes": [{"id": 798622144, "item_id": 49913884, "url": "https://news.ycombinator.com/item?id=49913884", "by": "deanc", "date": "2026-09-30", "stance": "warn", "quote": "I don't _want_ to use aistudio. The UX is confusing", "excerpt": "At this point I just think they are benchmaxxing and all talk and no action. I pay for AI plus because I wanted more storage, and when I go to gemini.google.com the most recent model I can use is 3.6-flash-lite. Two revisions have been released since then and they still can't put these things in the hands of customers. Why is it that other providers can get the models into the hands of customers right away? Google is", "context": "", "use_case": "", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 772409489, "item_id": 48275593, "url": "https://news.ycombinator.com/item?id=48275593", "by": "cafkafk", "date": "2026-05-25", "stance": "compare", "quote": "Google Vertex (or Google AI Studio) might be a potential alternative, but the UX is a lot worse", "excerpt": "Google Vertex (or Google AI Studio) might be a potential alternative, but the UX is a lot worse, and it can be hard to estimate cost since it's typically lagging. One of the advantages you'll miss when moving from openrouter is going from a \"debit\" based system to a \"credit\" based one. I.e. openrouter you pay up front, Google you're billed monthly based on usage.", "context": "", "use_case": "LLM API access", "switched_from": "", "story": "Ask HN: Some Sensible Alternative to Openrouter?"}, {"id": 735488880, "item_id": 45968055, "url": "https://news.ycombinator.com/item?id=45968055", "by": "Der_Einzige", "date": "2025-11-18", "stance": "compare", "quote": "I love the google AI studio, but I hate it too for not enabling a whole host of advanced features.", "excerpt": "When will they allow us to use modern LLM samplers like min_p, or even better samplers like top N sigma, or P-less decoding? They are provably SOTA and in some cases enable infinite temperature. Temperature continues to be gated to maximum of 0.2, and there's still the hidden top_k of 64 that you can't turn off. I love the google AI studio, but I hate it too for not enabling a whole host of advanced features. So many", "context": "", "use_case": "LLM prompting", "switched_from": "", "story": "Gemini 3"}]}, {"label": "Costs and limits", "summary": "Users report unexpected API bills, lagging cost estimates and a free tier limited to one or two requests.", "quotes": [{"id": 783013795, "item_id": 48938362, "url": "https://news.ycombinator.com/item?id=48938362", "by": "jdw64", "date": "2026-07-16", "stance": "warn", "quote": "In AI Studio, they say you have to use the API. You try it and get billed 80$", "excerpt": "I recommend that every AI user start with Gemini as their first AI. Use ChatGPT, and it's ask a question, get an answer, done. Tell it to code, get the code, done. But use Gemini? You get burned by the hallucinations Gemini casually spews out on a daily basis. You develop a habit of fact checking every single answer. You learn that blindly trusting the AI's response will get you absolutely screwed. AI answers must al", "context": "", "use_case": "", "switched_from": "", "story": "Google Gemini Launch Delayed as Tech Falls Short of Internal Goals"}, {"id": 772409489, "item_id": 48275593, "url": "https://news.ycombinator.com/item?id=48275593", "by": "cafkafk", "date": "2026-05-25", "stance": "compare", "quote": "Google Vertex (or Google AI Studio) might be a potential alternative, but the UX is a lot worse", "excerpt": "Google Vertex (or Google AI Studio) might be a potential alternative, but the UX is a lot worse, and it can be hard to estimate cost since it's typically lagging. One of the advantages you'll miss when moving from openrouter is going from a \"debit\" based system to a \"credit\" based one. I.e. openrouter you pay up front, Google you're billed monthly based on usage.", "context": "", "use_case": "LLM API access", "switched_from": "", "story": "Ask HN: Some Sensible Alternative to Openrouter?"}, {"id": 788669088, "item_id": 49291818, "url": "https://news.ycombinator.com/item?id=49291818", "by": "ac29", "date": "2026-08-13", "stance": "warn", "quote": "Last time I used the AI studio free tier it was limited to one or two requests, effectively useless.", "excerpt": "Last time I used the AI studio free tier it was limited to one or two requests, effectively useless. I think people are complaining its too hard to set up a paid API key (no reason you should make paying customers spend more than a few clicks and a minute of their time to pay you)", "context": "", "use_case": "Gemini API access", "switched_from": "", "story": "Gemini 3.7 Flash"}]}, {"label": "Data deletion", "summary": "One user reports that deleting a chat does not remove it server-side, and another is pursuing a data case.", "quotes": [{"id": 785683152, "item_id": 49105197, "url": "https://news.ycombinator.com/item?id=49105197", "by": "Bitu79", "date": "2026-07-29", "stance": "warn", "quote": "Google AI Studio\u2019s \u201cDelete\u201d button does not delete the server\u2011side chat.", "excerpt": "I found that Google AI Studio\u2019s \u201cDelete\u201d button does not delete the server\u2011side chat. I tested it by deleting a prompt, deleting the JSON file from Drive, and emptying the Trash. The file was fully gone. Then I used Google\u2019s official recovery tool. The JSON came back \u2014 and the model instantly continued the conversation with full context. This is only possible if the server\u2011side session and conversation were never del", "context": "", "use_case": "", "switched_from": "", "story": "Google AI Studio \"Delete\" doesn't delete \u2013 server chat persists (3 videos)"}, {"id": 796373408, "item_id": 49773338, "url": "https://news.ycombinator.com/item?id=49773338", "by": "Bitu79", "date": "2026-09-20", "stance": "warn", "quote": "a really ugly thing that they are stealing people's data", "excerpt": "Guys, please forgive me if my English is crappy. My native language is Hungarian, so I use AI to write my replies and the English articles. I've been working on this case for almost a year now, and I just want this big corporation to finally be held legally accountable! This whole thing has consumed so much of my time and my nerves. Honestly, it's starting to break me down a little. But I'm not backing down! It\u2019s a r", "context": "has spent almost a year pursuing a data deletion case", "use_case": "", "switched_from": "", "story": "Google AI Studio fakes data deletion. VRP auto-banned me in 60s for reporting it"}]}, {"label": "Sampling controls", "summary": "A commenter wants advanced samplers and complains about capped settings and a hidden top_k.", "quotes": [{"id": 735488880, "item_id": 45968055, "url": "https://news.ycombinator.com/item?id=45968055", "by": "Der_Einzige", "date": "2025-11-18", "stance": "compare", "quote": "I love the google AI studio, but I hate it too for not enabling a whole host of advanced features.", "excerpt": "When will they allow us to use modern LLM samplers like min_p, or even better samplers like top N sigma, or P-less decoding? They are provably SOTA and in some cases enable infinite temperature. Temperature continues to be gated to maximum of 0.2, and there's still the hidden top_k of 64 that you can't turn off. I love the google AI studio, but I hate it too for not enabling a whole host of advanced features. So many", "context": "", "use_case": "LLM prompting", "switched_from": "", "story": "Gemini 3"}]}, {"label": "CPU usage", "summary": "One commenter says the web app pegs a CPU core.", "quotes": [{"id": 782737456, "item_id": 48921091, "url": "https://news.ycombinator.com/item?id=48921091", "by": "MrBuddyCasino", "date": "2026-07-15", "stance": "warn", "quote": "Google Ai studio: pegs a core", "excerpt": "Google Ai studio: pegs a core Opencode: pegs a core Paypal: pegs a core Chatgpt: pegs a core", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Is it just me, or is software buggier across the board?"}]}], "who": [{"by": "gtadesktop1", "context": "banned from Claude", "url": "https://news.ycombinator.com/item?id=49675312", "date": "2026-09-12"}, {"by": "bpavuk", "context": "Android native dev", "url": "https://news.ycombinator.com/item?id=48339418", "date": "2026-05-30"}, {"by": "stingtao", "context": "not a programmer", "url": "https://news.ycombinator.com/item?id=46552349", "date": "2026-01-09"}], "tags": ["free tier", "for prototyping apps", "for prompt experimentation", "for non-programmers"], "use_cases": ["api key and prompt testing", "testing gemini models", "free llm access for app development", "forking and reverting llm prompts", "general chat", "gemini api access"], "compared": [{"slug": "claude-code", "name": "Claude Code", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "codex", "name": "Codex", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "claude", "name": "Claude", "co": 1, "switched_from": 1, "switched_to": 0}, {"slug": "gemini-cli", "name": "Gemini CLI", "co": 1, "switched_from": 0, "switched_to": 1}, {"slug": "antigravity", "name": "Antigravity", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "chatgpt", "name": "ChatGPT", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "openrouter", "name": "OpenRouter", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "cursor", "name": "Cursor", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49289112", "title": "Gemini 3.7 Flash", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=50276792", "title": "Gemini 4 Carbon", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49913571", "title": "Gemini 4 Argon", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49772544", "title": "Google AI Studio fakes data deletion. VRP auto-banned me in 60s for reporting it", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49715947", "title": "Gemini 3.8 Live and 3.8 Live Extended Thinking", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49672966", "title": "Ask HN: What default model do you use and why?", "mentions": 1}], "sentiment_by_month": {"2025-11": {"compare": 1}, "2025-12": {}, "2026-01": {"compare": 1, "neutral": 1}, "2026-02": {"neutral": 1}, "2026-03": {}, "2026-04": {}, "2026-05": {"compare": 1, "neutral": 1}, "2026-06": {"recommend": 1}, "2026-07": {"warn": 3}, "2026-08": {"neutral": 1, "recommend": 2, "warn": 1}, "2026-09": {"neutral": 2, "recommend": 2, "warn": 2}, "2026-10": {"warn": 1}}, "quotes": [{"id": 804586193, "item_id": 50286637, "url": "https://news.ycombinator.com/item?id=50286637", "by": "hypendev", "date": "2026-10-29", "stance": "warn", "quote": "I open the AI studio, the banner to update shows, then page reloads and it disappeared.", "excerpt": "I was confused a bit where this was. Then I had to Google Gemini, which lead me to gemini.google.com (did not know it existed, and I use gemini in prod via google cloud). First thing there that got me was that all of my Google searches. Why? I googled \"snoop dog real name\". Why is this considered a gemini chat now? If I actually used it, my chats would be buried under dumb quick google searches I did. And it seems it", "context": "uses Gemini in prod via Google Cloud", "use_case": "API key and prompt testing", "switched_from": "", "story": "Gemini 4 Carbon"}, {"id": 798622144, "item_id": 49913884, "url": "https://news.ycombinator.com/item?id=49913884", "by": "deanc", "date": "2026-09-30", "stance": "warn", "quote": "I don't _want_ to use aistudio. The UX is confusing", "excerpt": "At this point I just think they are benchmaxxing and all talk and no action. I pay for AI plus because I wanted more storage, and when I go to gemini.google.com the most recent model I can use is 3.6-flash-lite. Two revisions have been released since then and they still can't put these things in the hands of customers. Why is it that other providers can get the models into the hands of customers right away? Google is", "context": "", "use_case": "", "switched_from": "", "story": "Gemini 4 Argon"}, {"id": 796373408, "item_id": 49773338, "url": "https://news.ycombinator.com/item?id=49773338", "by": "Bitu79", "date": "2026-09-20", "stance": "warn", "quote": "a really ugly thing that they are stealing people's data", "excerpt": "Guys, please forgive me if my English is crappy. My native language is Hungarian, so I use AI to write my replies and the English articles. I've been working on this case for almost a year now, and I just want this big corporation to finally be held legally accountable! This whole thing has consumed so much of my time and my nerves. Honestly, it's starting to break me down a little. But I'm not backing down! It\u2019s a r", "context": "has spent almost a year pursuing a data deletion case", "use_case": "", "switched_from": "", "story": "Google AI Studio fakes data deletion. VRP auto-banned me in 60s for reporting it"}, {"id": 795825488, "item_id": 49739093, "url": "https://news.ycombinator.com/item?id=49739093", "by": "Gareth321", "date": "2026-09-17", "stance": "neutral", "quote": "AI Studio is intended for serious work.", "excerpt": "I used [AI Studio.](https://aistudio.google.com/) It's possible the same issues are present there, but AI Studio is intended for serious work. I don't see why they would intentionally hobble the model's capabilities in AI Studio.", "context": "", "use_case": "testing Gemini models", "switched_from": "", "story": "Gemini 3.8 Live and 3.8 Live Extended Thinking"}, {"id": 794804992, "item_id": 49675312, "url": "https://news.ycombinator.com/item?id=49675312", "by": "gtadesktop1", "date": "2026-09-12", "stance": "recommend", "quote": "in the Playground-Mode you don't pay one cent", "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": "banned from Claude", "use_case": "free LLM access for app development", "switched_from": "Claude", "story": "Ask HN: What default model do you use and why?"}, {"id": 794024608, "item_id": 49626538, "url": "https://news.ycombinator.com/item?id=49626538", "by": "dwringer", "date": "2026-09-09", "stance": "recommend", "quote": "I used to use Google's AI Studio a lot and fork it after every successful prompt interaction", "excerpt": "I only made it through the first round of prompt selection; both options for the second step were equally pointless and not at all prompts I would ever expect to result in a constructive outcome. In my experience, telling the model it screwed up without specifically addressing, unambiguously, how to fix it, only leads to more suffering. If this page illustrates nothing else, I think it shows the immense downside of t", "context": "", "use_case": "forking and reverting LLM prompts", "switched_from": "", "story": "Claude, change the \u201cAdd to Cart\u201d button to blue"}, {"id": 792623216, "item_id": 49538951, "url": "https://news.ycombinator.com/item?id=49538951", "by": "scrlk", "date": "2026-09-02", "stance": "neutral", "quote": "I use Gemini through Google AI Studio as my general chat model", "excerpt": "That's interesting to hear. I should have added that I use Gemini through Google AI Studio as my general chat model, which probably explains our wildly different experiences.", "context": "", "use_case": "general chat", "switched_from": "", "story": "Gemini 3.8 Flash and 3.8 Flash Cyber"}, {"id": 788669088, "item_id": 49291818, "url": "https://news.ycombinator.com/item?id=49291818", "by": "ac29", "date": "2026-08-13", "stance": "warn", "quote": "Last time I used the AI studio free tier it was limited to one or two requests, effectively useless.", "excerpt": "Last time I used the AI studio free tier it was limited to one or two requests, effectively useless. I think people are complaining its too hard to set up a paid API key (no reason you should make paying customers spend more than a few clicks and a minute of their time to pay you)", "context": "", "use_case": "Gemini API access", "switched_from": "", "story": "Gemini 3.7 Flash"}, {"id": 788658496, "item_id": 49291156, "url": "https://news.ycombinator.com/item?id=49291156", "by": "qlte", "date": "2026-08-13", "stance": "recommend", "quote": "consider it the most dead simple/fastest dev dashboard to get started compared to the others like OpenAI/Anthropic", "excerpt": "I didn't have that issue back when I originally created my API keys a couple years ago. Just out of curiosity I switched to a different Google account that had never interacted with AI Studio and never used Google Cloud console. It was literally two clicks, and didn't even leave the page: the dialog asked to create a project and type in a name, I did that, clicked submit and then it was selected as the default projec", "context": "", "use_case": "Gemini API keys", "switched_from": "", "story": "Gemini 3.7 Flash"}, {"id": 788638912, "item_id": 49289932, "url": "https://news.ycombinator.com/item?id=49289932", "by": "axus", "date": "2026-08-13", "stance": "recommend", "quote": "It's on Google AI Studio, which I use for free when I'm not on computers I control.", "excerpt": "It's on Google AI Studio, which I use for free when I'm not on computers I control. It did fine on my usual benchmark about configuring old Sparc hardware, maybe output slightly faster than before. Even included something new to check in the firmware.", "context": "", "use_case": "free model access", "switched_from": "", "story": "Gemini 3.7 Flash"}, {"id": 787762066, "item_id": 49235129, "url": "https://news.ycombinator.com/item?id=49235129", "by": "thread123", "date": "2026-08-09", "stance": "neutral", "quote": "I had a lot of chats in OpenRouter, google AI Studio and lm studio", "excerpt": "I had a lot of chats in OpenRouter, google AI Studio and lm studio and no good way to view/search/combine them together. ThreadShelf started as a local archive with semantic search/MCP, and later grew support for continuing conversations through llama.cpp or OpenRouter. https://github.com/ChrystianSchutz/ThreadShelf It is my first time creating oss so please be gentle.", "context": "", "use_case": "LLM chats", "switched_from": "", "story": "Ask HN: What are you working on? (August 2026)"}, {"id": 785683152, "item_id": 49105197, "url": "https://news.ycombinator.com/item?id=49105197", "by": "Bitu79", "date": "2026-07-29", "stance": "warn", "quote": "Google AI Studio\u2019s \u201cDelete\u201d button does not delete the server\u2011side chat.", "excerpt": "I found that Google AI Studio\u2019s \u201cDelete\u201d button does not delete the server\u2011side chat. I tested it by deleting a prompt, deleting the JSON file from Drive, and emptying the Trash. The file was fully gone. Then I used Google\u2019s official recovery tool. The JSON came back \u2014 and the model instantly continued the conversation with full context. This is only possible if the server\u2011side session and conversation were never del", "context": "", "use_case": "", "switched_from": "", "story": "Google AI Studio \"Delete\" doesn't delete \u2013 server chat persists (3 videos)"}, {"id": 783013795, "item_id": 48938362, "url": "https://news.ycombinator.com/item?id=48938362", "by": "jdw64", "date": "2026-07-16", "stance": "warn", "quote": "In AI Studio, they say you have to use the API. You try it and get billed 80$", "excerpt": "I recommend that every AI user start with Gemini as their first AI. Use ChatGPT, and it's ask a question, get an answer, done. Tell it to code, get the code, done. But use Gemini? You get burned by the hallucinations Gemini casually spews out on a daily basis. You develop a habit of fact checking every single answer. You learn that blindly trusting the AI's response will get you absolutely screwed. AI answers must al", "context": "", "use_case": "", "switched_from": "", "story": "Google Gemini Launch Delayed as Tech Falls Short of Internal Goals"}, {"id": 782737456, "item_id": 48921091, "url": "https://news.ycombinator.com/item?id=48921091", "by": "MrBuddyCasino", "date": "2026-07-15", "stance": "warn", "quote": "Google Ai studio: pegs a core", "excerpt": "Google Ai studio: pegs a core Opencode: pegs a core Paypal: pegs a core Chatgpt: pegs a core", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Is it just me, or is software buggier across the board?"}, {"id": 775825648, "item_id": 48489103, "url": "https://news.ycombinator.com/item?id=48489103", "by": "manimonji", "date": "2026-06-11", "stance": "recommend", "quote": "I used google AI studio, and it designed the thing very well", "excerpt": "It's just that when I was exploring different things, I really liked front-end and I put more time on that. Recently I used google AI studio, and it designed the thing very well, and I sucked at designing and slow in developing. In other areas, it helped me a lot, for example Laravel docs looked hard to learn for me and I just used php or node js or Django or whatever to avoid Laravel instead, but then I just wanted ", "context": "", "use_case": "front-end design and prototyping", "switched_from": "", "story": "Why would someone want to learn code when AI does it better and faster?"}, {"id": 773430692, "item_id": 48339418, "url": "https://news.ycombinator.com/item?id=48339418", "by": "bpavuk", "date": "2026-05-30", "stance": "neutral", "quote": "you can vibecode Android apps in Google AI Studio with streaming from a Google-hosted device", "excerpt": "Android native dev here. > What is going on in the world of pure IOS/Android app development? I'll speak only for Android. I am tired of Google breaking source compatibility with every AndroidX release and remaining on outdated IntelliJ Platform versions in Android Studio. not too long ago, Google released AGP 9.0, which was a SHOCKWAVE for many Android projects. many compiler plugins' compatibility, including Google", "context": "Android native dev", "use_case": "vibe coding Android apps", "switched_from": "", "story": "Ask HN: What Is the State of App Development in 2026?"}, {"id": 772409489, "item_id": 48275593, "url": "https://news.ycombinator.com/item?id=48275593", "by": "cafkafk", "date": "2026-05-25", "stance": "compare", "quote": "Google Vertex (or Google AI Studio) might be a potential alternative, but the UX is a lot worse", "excerpt": "Google Vertex (or Google AI Studio) might be a potential alternative, but the UX is a lot worse, and it can be hard to estimate cost since it's typically lagging. One of the advantages you'll miss when moving from openrouter is going from a \"debit\" based system to a \"credit\" based one. I.e. openrouter you pay up front, Google you're billed monthly based on usage.", "context": "", "use_case": "LLM API access", "switched_from": "", "story": "Ask HN: Some Sensible Alternative to Openrouter?"}, {"id": 753227392, "item_id": 47076712, "url": "https://news.ycombinator.com/item?id=47076712", "by": "benatkin", "date": "2026-02-19", "stance": "neutral", "quote": "I used the AI studio link and tried running it with the temperature set to 1.75", "excerpt": "I used the AI studio link and tried running it with the temperature set to 1.75: https://jsbin.com/locodaqovu/edit?html,output", "context": "", "use_case": "testing Gemini 3.1 Pro", "switched_from": "", "story": "Gemini 3.1 Pro"}, {"id": 744837587, "item_id": 46552349, "url": "https://news.ycombinator.com/item?id=46552349", "by": "stingtao", "date": "2026-01-09", "stance": "neutral", "quote": "I used Cursor / Codex / Claude CLI / AI Studio / Antigravity and made many websites.", "excerpt": "I am not a programmer. I used Cursor / Codex / Claude CLI / AI Studio / Antigravity and made many websites. For me, I get 1000x AI dev since my initial comparison point is very very low. I created: https://live.stingtao.info for me to do interactive live quiz (like Kahoot) https://presentation.stingtao,.info for me to make presentations by AI (like gamma) https://catsbook.stingtao.info for cats to register their own ", "context": "not a programmer", "use_case": "building websites", "switched_from": "", "story": "AI Coding Assistants Are Getting Worse"}, {"id": 743470119, "item_id": 46466882, "url": "https://news.ycombinator.com/item?id=46466882", "by": "submeta", "date": "2026-01-02", "stance": "compare", "quote": "Disagree. I use Claude Code and Codex daily", "excerpt": "> The context is king Agree > and AI Studio is the only serious product for human-in-the-loop SWE Disagree. I use Claude Code and Codex daily, and I couldn\u2019t be happier. Had started with Cursor, switched to CLI based agents and never looked back. I use WezTerm, tmux, neovim, Zoxide, and create several tabs and panes and run claude code not only for vibe coding, scripting, analysing files, letting it write concepts, t", "context": "", "use_case": "human-in-the-loop SWE", "switched_from": "", "story": "Vibe Coding Killed Cursor"}, {"id": 735488880, "item_id": 45968055, "url": "https://news.ycombinator.com/item?id=45968055", "by": "Der_Einzige", "date": "2025-11-18", "stance": "compare", "quote": "I love the google AI studio, but I hate it too for not enabling a whole host of advanced features.", "excerpt": "When will they allow us to use modern LLM samplers like min_p, or even better samplers like top N sigma, or P-less decoding? They are provably SOTA and in some cases enable infinite temperature. Temperature continues to be gated to maximum of 0.2, and there's still the hidden top_k of 64 that you can't turn off. I love the google AI studio, but I hate it too for not enabling a whole host of advanced features. So many", "context": "", "use_case": "LLM prompting", "switched_from": "", "story": "Gemini 3"}]}