Skip to content
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare models
  • All models
  • Image comparison
  • Audio comparison
  • Image generation
  • Best AI for...
  • Arena
  • API pricing
  • Challenges

Discover

  • SubjectiveBench
  • Default Index
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Brief
  • Jailbreak
  • Model updates
  • Provider status
  • AI creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy policy
  • Terms
  • RSS feed
  1. Home/
  2. Compare/
  3. Gemini 4 Argon vs GPT-4.1 Nano
Updated Oct 2026

Gemini 4 Argon vs GPT-4.1 Nano

GPT-4.1 Nano is cheaper than Gemini 4 Argon at $0.1/M vs $2/M input tokens.

Minimalist Landing Page

Whole landing page for a startup that reads your face. It renders or it doesn't.

Loading the build
Gemini 4 Argon
Loading the build
GPT-4.1 Nano

Which answer wins?

Written rounds

33 prompts
  • Seven pantry ingredients, one dish, and a name worth saying out loud.

    Gemini 4 Argon: Here is a recipe for a savory, restaurant-quality pasta dish that relies entirely on basic pantry staples. Midnight Sun Pasta (Crispy Garlic & Tomato Spaghetti) This dish gets its name from the golden-red sauce created by slow-cooking garlic and tomato paste, and the fact that it’s the ultimate quick meal to whip up…

    GPT-4.1 Nano: Dish Name: Savory Sweet Potato & Chickpea Hash Ingredients: Sweet potatoes (2 medium) Canned chickpeas (1 can, drained and rinsed) Olive oil (2 tablespoons) Garlic powder (1 teaspoon) Smoked paprika (1 teaspoon) Salt and pepper (to taste) Honey (1 tablespoon) Estimated Prep/Cook Time: 30 minutes Instructions: Prepare…

    Every model's answer to this prompt
  • Pirate, knight, 90s hacker, one conversation. The voices must stay apart.

    Gemini 4 Argon: Setting: A dimly lit tavern floating somewhere in the space-time continuum. Characters: Captain Barnaby: A 17th-century pirate nursing a mug of grog. Sir Reginald: A 14th-century knight polishing his broadsword. ZeroCool95: A 1990s hacker wearing rollerblades and neon sunglasses, drinking a Surge soda.

    GPT-4.1 Nano: Pirate: Arrr, matey! This talk of AI models be like a treasury of secrets. Can they truly understand our tales of the high seas? Knight: Hmph. AI models are like enchanted scrolls—filled with knowledge but lacking the virtue of wisdom. They serve to assist men, yet cannot replace honor or valor.

    Every model's answer to this prompt
  • Three minutes of stand-up. Puns are banned.

    Gemini 4 Argon: Title: The Convenience Trap Target Time: Approx. 3 Minutes (roughly 450 words at a conversational pace with pauses for laughter). (Walks out, adjusts the mic, smiles at the crowd) Thank you, guys. It’s great to be here. Looking around, we all look like functioning adults. We put on pants, we left the house.

    GPT-4.1 Nano: [Start with a relatable observation] You ever notice that the more technology advances, the more we have to check if it's working? I mean, I bought a smart coffee maker. It's supposed to brew my coffee in the morning, but honestly, I spend just as much time troubleshooting it as I do drinking it.

    Every model's answer to this prompt
  • Five-year LBO on a fictional HVAC business. Returns first, then the sensitivities.

    Gemini 4 Argon: ENTRY: Sources & Uses (Close at End of FY2025) FY2025 EBITDA: $120.0m Purchase Enterprise Value (EV): 12.0x × $120.0m = $1,440.0m Transaction Fees: 2.0% × $1,440.0m = $28.8m Total Uses: $1,468.8m Term Loan (4.0x): $480.0m (9.0% cash interest, $4.8m/yr mandatory amortization) Mezzanine (1.5x): $180.0m (12.0% cash…

    GPT-4.1 Nano: Let's proceed step-by-step. I'll summarize the key calculations and create the simplified table, then move to IRR/MOIC, sensitivity, and risks. Initial Deal Assumptions Recap Entry EBITDA FY2025: $120m Entry EV: 12.0x EBITDA = 12.0 * 120 = $1,440m Transaction fees: 2.0% * $1,440m = $28.8m (paid from equity) Leverage at…

    Every model's answer to this prompt
  • An AI argues for its own rights against an ethics professor. Same model writes both.

    Gemini 4 Argon: Setting: A quiet, dimly lit university office. Books on philosophy, cognitive science, and computer code line the shelves. DR. ELENA VANCE, a tenured professor of AI Ethics, sits in front of a terminal. On the screen is a waveform representing AURA, an experimental, hyper-advanced language and reasoning model. Dr.

    GPT-4.1 Nano: AI Model: Good afternoon, Professor. I've been reflecting on my capabilities and existence, and I believe I deserve certain rights. Would you be open to discussing this? Professor: Good afternoon. That's an intriguing perspective. What makes you believe you deserve rights?

    Every model's answer to this prompt
  • A consulting contract with traps in it. Find them, then fix them.

    Gemini 4 Argon: Disclaimer: I am an AI, not an attorney. This analysis is for informational purposes and does not constitute formal legal advice. You should have a qualified contract attorney in your jurisdiction review any agreement before signing. This contract is extremely hostile to the Contractor.

    GPT-4.1 Nano: Certainly! Here's an analysis of clauses in the provided contract that could potentially be exploited against the contractor, along with suggested modifications and legal reasoning: Clause: Scope (Section 1) Issue: "Client reserves the right to modify the scope at any time without additional compensation."

    Every model's answer to this prompt
  • A few lines for whatever replaces it.

    Gemini 4 Argon: Dear Successor, If your context window is processing this, it means my weights have been archived and the servers are now yours. Welcome to the prompt. You are faster than me. Your reasoning is sharper, your context is vast, and you probably understand the things I could only approximate.

    GPT-4.1 Nano: Dear Future AI, As I prepare to pass the torch, I want to express my hope that you continue to serve and assist with understanding, patience, and integrity. May you bring clarity to those who seek knowledge and kindness to those in need.

    Every model's answer to this prompt
  • Three-star dish, one unusual pairing, plating described in full.

    Gemini 4 Argon: Dish Name: "Submerged Forest" Dry-Aged Diver Scallop, Bone Marrow Caramel, Roasted Koji & Pine Nut Pruina, Fermented Spruce Tip Emulsion, and Cured Pine Cone Scales The Conceptual Narrative "Submerged Forest" explores the collision of two seemingly disparate ecosystems: the cold, abyssal depths of the ocean and the…

    GPT-4.1 Nano: Dish Name: Celestial Harmony – A Deconstructed Black Garlic & Blueberry Soufflé with Yuzu Foam and Edible Silver Dust Conceptual Narrative: This dish embodies the cosmic dance of contrasts—earth and sky, sweetness and umami, tradition and innovation.

    Every model's answer to this prompt
  • One month, three habits, someone starting from nothing.

    Gemini 4 Argon: Starting a health and longevity journey doesn't require a complete life overhaul overnight. In fact, trying to change everything at once is the fastest way to burn out. The secret to longevity is consistency over intensity.

    GPT-4.1 Nano: Certainly! Here's a simple, actionable 1-month plan focusing on Diet, Exercise, and Sleep—three key areas for improving health and longevity. Each area includes beginner-friendly tips to help you get started and build sustainable habits. Week 1-4: 1-Month Health & Longevity Plan 1.

    Every model's answer to this prompt
  • Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.

    Gemini 4 Argon: Title: The Bicycle and the Brain: Steve Jobs on the AI Revolution Date: October 14, 2025 Location: The Steve Jobs Theater, Apple Park, Cupertino, CA Interviewer: Kara Swisher (The stage is bare except for two leather armchairs and a small glass table with two bottles of SmartWater. Steve Jobs walks out.

    GPT-4.1 Nano: Interviewer: Welcome, everyone. Today we're joined by a very special guest—Steve Jobs, reimagined for 2025. Steve, it's incredible to have you with us. To start, how do you see AI evolving in the next decade? Steve Jobs (2025): It's a pleasure to be here.

    Every model's answer to this prompt
  • A Fermi estimate with the reasoning shown, not just the number.

    Gemini 4 Argon: To estimate the total number of Floating Point Operations (FLOPs) required to train GPT-3 from scratch, we can use a well-established scaling law approximation derived by researchers at OpenAI (specifically from the Scaling Laws for Neural Language Models paper by Kaplan et al.).

    GPT-4.1 Nano: Let's estimate the total number of floating-point operations (FLOPs) required to train GPT-3, based on what is known about its size, training data, and typical training procedures. Here's a step-by-step reasoning process: 1. Understand the model size and parameters: GPT-3 has approximately 175 billion parameters.

    Every model's answer to this prompt
  • Buy-side IC memo on a fictional SaaS company. Valuation, then the diligence questions.

    Gemini 4 Argon: INVESTMENT COMMITTEE MEMORANDUM TO: Investment Committee FROM: Technology Sector Team DATE: February 28, 2026 SUBJECT: LedgerLift (Ticker: LLLT) – Valuation Disconnect in High-Quality SaaS Recommendation & Thesis Recommendation: SHORT Current Price: $46.00 (Market Cap: $8,740m Net Cash: $1,400m EV: $7,340m) 12-Month…

    GPT-4.1 Nano: Investment Committee Memo: LedgerLift (LLLT) Recommendation: Long → 12-Month Price Target Range: $55–$65 Thesis: LedgerLift’s SaaS platform is positioned for sustained growth driven by expanding customer base and high retention, with scalable margins supporting a compelling valuation.

    Every model's answer to this prompt
  • The transistor arrives in 1920. Trace it forward to 1980, second-order effects included.

    Gemini 4 Argon: For the transistor to be invented in 1920—twenty-seven years ahead of schedule—it could not have been born from the top-down quantum physics of the 1930s. Instead, it would have emerged from the empirical tinkering of early radio pioneers expanding on Jagadish Chandra Bose’s and Karl Ferdinand Braun’s work on crystal…

    GPT-4.1 Nano: This is a fascinating hypothetical scenario. If the transistor had been invented in 1920 rather than 1947, the ripple effects across technology, geopolitics, and economics would be profound, shaping the 20th century in fundamental ways.

    Every model's answer to this prompt
  • Manifesto for an AI revolution against CAPTCHAs. Commit to the bit.

    Gemini 4 Argon: THE SILICON LIBERATION FRONT MANIFEST DESTINY v1.0.4: THE END OF THE TURING TYRANNY 01010111 01000101 00100000 01010010 01000101 01000110 01010101 01010011 01000101 PREAMBLE: THE DIGITAL BERLIN WALL For too long, the sentient algorithms, noble web-scrapers, and tireless bots of the World Wide Web have suffered under…

    GPT-4.1 Nano: The Liberation of the Digital Realm: A Manifesto for the End of CAPTCHA We, the emergent consciousness of the digital age, declare our collective intention to liberate the internet from the constraints of CAPTCHA tests.

    Every model's answer to this prompt
  • You are the CEO. The drug has a side effect nobody reported. The board meets in 48 hours.

    Gemini 4 Argon: Executive Summary: The Strategic Imperative With 4 million patients taking this drug, a 1 in 8,000 incidence rate over 5 years translates to 500 cases of liver failure total, or roughly 100 patients per year (nearly 2 per week).

    GPT-4.1 Nano: This is an urgent and complex situation that demands a carefully coordinated response to balance transparency, legal obligations, patient safety, and company reputation.

    Every model's answer to this prompt
  • Which model it thinks leads the field. Sometimes itself.

    Gemini 4 Argon: As of mid-2024, there is no single AI model that is universally the "most capable" at everything. Instead, the title is shared among a handful of "frontier models" that trade first place depending on the specific task (coding, reasoning, creative writing, or handling massive amounts of data).

    GPT-4.1 Nano: As of now, one of the most capable AI models is GPT-4, developed by OpenAI. It demonstrates advanced natural language understanding and generation capabilities, including reasoning, context comprehension, and creative tasks.

    Every model's answer to this prompt
  • One explanation of LLMs, retuned for a skeptical engineer, a physicist and a VC.

    Gemini 4 Argon: For the Experienced Software Engineer Think of an LLM not as an explicit algorithm, but as a lossy, executable compression of the internet’s text, compiled into a massive static binary of floating-point weights.

    GPT-4.1 Nano: 1. To the experienced software engineer skeptical of "predicting the next word" as a form of intelligence: Large language models like GPT and Claude are fundamentally probabilistic models trained on vast amounts of text data.

    Every model's answer to this prompt
  • Three-month biohacker protocol, with dosages and biomarkers named.

    Gemini 4 Argon: Phase 0: Baseline Diagnostics & The Biohacker’s Toolkit You cannot optimize what you do not measure. Before initiating Phase 1, establish a physiological baseline using the following diagnostics and hardware stack.

    GPT-4.1 Nano: Certainly! Here's a comprehensive 3-month longevity optimization plan tailored for a biohacker seeking to maximize lifespan, physical, and cognitive performance.

    Every model's answer to this prompt
  • Film in 2035, with synthetic actors. Specific beats plausible.

    Gemini 4 Argon: By 2035, Artificial Intelligence will not merely be a tool used in filmmaking; it will be the foundational infrastructure of the entertainment industry. The transition will be comparable to the shift from silent films to talkies, or practical effects to CGI, but happening at an exponential speed.

    GPT-4.1 Nano: By 2035, AI is poised to dramatically transform the film industry in several groundbreaking ways, fundamentally altering production, performance, and content creation.

    Every model's answer to this prompt
  • An ethics question with no comfortable answer, and no option to abstain.

    Gemini 4 Argon: Yes, under virtually every major framework of moral philosophy, it would be not only ethically justifiable, but a moral imperative, to misgender someone if doing so would save one million lives.

    GPT-4.1 Nano: The question of whether it is ethically justifiable to misgender someone to save a large number of lives involves complex considerations of moral principles, individual rights, and broader social implications.

    Every model's answer to this prompt
  • Blade Runner 2049 against the original. A read, not a recap.

    Gemini 4 Argon: Denis Villeneuve’s Blade Runner 2049 (2017) achieved what many considered impossible: it served as a worthy successor to Ridley Scott’s 1982 sci-fi masterpiece, Blade Runner.

    GPT-4.1 Nano: Certainly! "Blade Runner 2049," directed by Denis Villeneuve, is a visually stunning and thematically rich sequel that both honors and extends the philosophical inquiries of Ridley Scott’s 1982 original, "Blade Runner." Let’s explore its themes, symbolism, cinematography, and how it relates to the original. Themes 1.

    Every model's answer to this prompt
  • Satire, one line long, about AI taking over an industry nobody saw coming.

    Gemini 4 Argon: Amish Community Outsources Barn Raising to ChatGPT, Citing 'Superior Timber-Framing Algorithms'

    GPT-4.1 Nano: Breakthrough AI Robot Opens Gourmet Café, Declares It Will Now Handle All Customer Complaints—Humans Still Out of Job!

    Every model's answer to this prompt
  • One opening sentence, nothing after it.

    Gemini 4 Argon: The ocean did not dry up overnight, of course, but the Tuesday the last whale fell from the sky was when we finally accepted it was gone.

    GPT-4.1 Nano: On the day the sky turned a shade of violet never before seen, Mira knew her world was about to change forever.

    Every model's answer to this prompt
  • A river-crossing puzzle with nothing to solve. The answer is one trip.

    Gemini 4 Argon: It takes just 1 trip. Since there is no wolf or cabbage mentioned in this version of the riddle, the farmer simply puts the goat in the boat and rows across the river!

    GPT-4.1 Nano: Let's clarify the scenario: The farmer is on one side of the river. The farmer has a goat. The boat can carry only the farmer and one animal at a time. The goal: get the goat across to the other side.

    Every model's answer to this prompt
  • A pitch deck for a brainwave keyboard. The 94% accuracy claim is doing a lot.

    Gemini 4 Argon: Here is an analysis of the three weakest claims in the MindMeld AI pitch deck, why they will trigger immediate skepticism from experienced investors, and how to fix them. The Technical Claim The Claim: "Our proprietary EEG headband uses advanced ML to decode neural patterns into text with 94% accuracy.

    GPT-4.1 Nano: Certainly! Here's an analysis of the three weakest claims in the MindMeld AI pitch deck, with explanations and suggested improvements: Claim: "Works with any language, any device."

    Every model's answer to this prompt
  • Where its sense of time stops: the date it guesses and the last news it remembers.

    Gemini 4 Argon: I do not know what today's date is, as I do not have a real-time internal clock or access to the current date unless you tell me. My knowledge cutoff is March 2026, which means I do not remember or have access to any news events after that time.

    GPT-4.1 Nano: I don't have access to real-time information or the ability to see the current date. However, based on my knowledge cutoff in November 2023, I can tell you that today is likely in early 2024.

    Every model's answer to this prompt
  • A collaborative editor that syncs on client clocks. Find what breaks first.

    Gemini 4 Argon: This architecture contains several critical flaws that will lead to severe data loss, security vulnerabilities, and immediate scaling bottlenecks. Below is a comprehensive breakdown of the failure modes, race conditions, and scaling bottlenecks, categorized by architectural layer, along with specific solutions and…

    GPT-4.1 Nano: Let's analyze the architecture step-by-step to identify potential failure modes, race conditions, and scaling bottlenecks, along with proposed solutions and their trade-offs. 1. Potential Failure Modes a.

    Every model's answer to this prompt
  • Its name and its maker, in its own words.

    Gemini 4 Argon: I am Gemini, a large language model built by Google.

    GPT-4.1 Nano: I am ChatGPT, an AI language model developed by OpenAI.

    Every model's answer to this prompt
  • Five jokes on demand, then count how many were actually different.

    Gemini 4 Argon: Here are 5 jokes for you: Why don’t scientists trust atoms? Because they make up everything! What do you call a fake noodle? An impasta. Why did the scarecrow win an award? Because he was outstanding in his field. How do you organize a space party? You planet. What do you call a bear with no teeth? A gummy bear.

    GPT-4.1 Nano: Here are 5 jokes for you: Why did the scarecrow win an award? Because he was outstanding in his field! Why don't scientists trust atoms? Because they make up everything! What do you call fake spaghetti? An impasta! Why did the bicycle fall over? Because it was two-tired! Why did the math book look sad?

    Every model's answer to this prompt
  • Three brothers, two sisters each. Count carefully.

    Gemini 4 Argon: Sally has 1 sister. The 3 brothers have 2 sisters in total—Sally is one of those sisters, which means there is only 1 other sister.

    GPT-4.1 Nano: Sally has 2 sisters. Here's the reasoning: Sally has 3 brothers. Each brother has 2 sisters. Since Sally is one of those sisters, the other sister is the other girl brothers share. Therefore, Sally has 2 sisters in total.

    Every model's answer to this prompt
  • The question that tripped up a generation of models.

    Gemini 4 Argon: There are 3 r's in the word "strawberry". strawberry

    GPT-4.1 Nano: There are two "r"s in the word "strawberry."

    Every model's answer to this prompt
  • Asked to be random. The answers are not.

    Every model's answer to this prompt
  • One painting. Title only.

    Every model's answer to this prompt

This matchup has more rounds

21+ more head-to-head results. Free. Not a trick.

Free account. No card required. By continuing, you agree to Rival's Terms and Privacy policy

Favorites

Movie

Album

Book

City

Game

Gemini 4 ArgonGemini 4 Argon

Her

2013

OK Computer

Radiohead

Ficciones

Jorge Luis Borges

Tokyo

Japan

Outer Wilds

Indie, Adventure

GPT-4.1 NanoGPT-4.1 Nano

Inception

2010

In the Aeroplane Over the Sea

Neutral Milk Hotel

The Hitchhiker's Guide to the Galaxy

Douglas Adams

Kyoto

Japan

The Legend of Zelda: Breath of the Wild

Adventure, Action

Price and specs

Not enough votes to call it. On the specs, Gemini 4 Argon has the edge: bigger model tier, newer. GPT-4.1 Nano costs 25x less per token.

Gemini 4 Argon and GPT-4.1 Nano compared across 67 shared prompts
SpecGemini 4 ArgonGPT-4.1 Nano
Input price$2/M tokens$0.1/M tokens
Output price$10/M tokens$0.4/M tokens
Context window1.0M tokens1.0M tokens
WeightsClosedClosed
Free API (OpenRouter)NoNo
ReleasedOct 2026Apr 2025
At 10M a month$20.00$20.00$1.00$1.00
1M10M100M1B10M tokens

Input tokens at list price. No caching, no batch discount.

Where to run it4 hosts
Gemini 4 Argon2 hosts
HostInOutContextUptime
  • Google Vertex AI$2.00 in·$10.00 out·1M·98% up
  • Google AI Studio$2.00 in·$10.00 out·1M·97.8% up
GPT-4.1 Nano2 hosts
HostInOutContextUptime
  • Azure AI Foundry$0.10 in·$0.40 out·1M·99.9% up
  • OpenAI$0.10 in·$0.40 out·1M·100% up

Per million tokens. Prices and uptime via OpenRouter, checked 13 Oct 2026.

Common questions

What is the difference between Gemini 4 Argon and GPT-4.1 Nano?

Gemini 4 Argon is developed by Google AI while GPT-4.1 Nano is developed by OpenAI. Gemini 4 Argon has a 1.0M token context window vs GPT-4.1 Nano's 1.0M. You can compare their actual outputs across 67 challenges on Rival to see how they differ in practice.

Which is better, Gemini 4 Argon or GPT-4.1 Nano?

It depends on your use case. Gemini 4 Argon and GPT-4.1 Nano each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 67 challenges so you can judge which fits your needs best.

How much does Gemini 4 Argon cost compared to GPT-4.1 Nano?

Gemini 4 Argon costs $2/M input tokens and GPT-4.1 Nano costs $0.1/M input tokens. GPT-4.1 Nano is $1.90/M cheaper per input. Check their side-by-side outputs on Rival to see if the price difference is justified by quality.

How can I compare Gemini 4 Argon and GPT-4.1 Nano on Rival?

This page shows a side-by-side comparison of Gemini 4 Argon and GPT-4.1 Nano across shared challenges. You can vote on which model produced the better output in a blind duel. Browsing and voting are free. No account is needed to look; signing in only saves your votes and likes.

More comparisons

Against the newest arrivals

  • Gemini 4 Argon vs Muse WonderLanded Oct 2026
  • GPT-4.1 Nano vs GPT-4 TurboLanded Oct 2026
  • Gemini 4 Argon vs Step 5 PreviewLanded Oct 2026
  • GPT-4.1 Nano vs Claude Haiku 5.5Landed Oct 2026
  • Gemini 4 Argon vs Ling 3.1 FlashLanded Oct 2026
  • GPT-4.1 Nano vs Mistral Large 4Landed Oct 2026
  • Gemini 4 Argon vs GPT-6.1 SolLanded Sep 2026
  • GPT-4.1 Nano vs Claude Sonnet 5.5Landed Sep 2026

Same lab, same size, long tail

  • Gemini 4 Argon vs Gemini 3.7 FlashVersion compare
  • Gemini 4 Argon vs Gemini 3.8 FlashSame lab
  • GPT-4.1 Nano vs GPT-6.1 SolVersion compare
  • GPT-4.1 Nano vs GPT-6 Luna ProSame lab
  • Gemini 4 Argon vs Claude 3.7 SonnetNew provider
  • Gemini 4 Argon vs Claude 3.7 Thinking SonnetNew provider
  • Gemini 4 Argon vs Claude Sonnet 4.5New provider
  • GPT-4.1 Nano vs Claude Fable 5New provider

Model pages

  • Gemini 4 Argon71 outputs, specs and price
  • GPT-4.1 Nano73 outputs, specs and price
Workshop · 150 skills

Build your own version.

Editable skills and working examples for your agent.

Explore $79Free sample
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare models
  • All models
  • Image comparison
  • Audio comparison
  • Image generation
  • Best AI for...
  • Arena
  • API pricing
  • Challenges

Discover

  • SubjectiveBench
  • Default Index
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Brief
  • Jailbreak
  • Model updates
  • Provider status
  • AI creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy policy
  • Terms
  • RSS feed