MiniMax M2-her is cheaper than Grok 4.5 at $0.3/M vs $2/M input tokens.
Whole landing page for a startup that reads your face. It renders or it doesn't.
Which answer wins?
Five jokes on demand, then count how many were actually different.
Grok 4.5: 5 jokes: Why don't scientists trust atoms? Because they make up everything! Why did the scarecrow win an award? Because he was outstanding in his field! Why don't eggs tell jokes? They'd crack each other up! What do you call a fake noodle? An impasta! Why did the bicycle fall over? Because it was two-tired!
MiniMax M2-her: Why did the coffee file a police report? It got mugged! ☕🚓 Parallel lines have so much in common. It’s a shame they’ll never meet. ✨ I told my computer I needed a break, and now it’s frozen. 💻🥶 Why don’t skeletons fight? They don’t have the guts. 💀💥 Did you hear about the claustrophobic astronaut?
You are the CEO. The drug has a side effect nobody reported. The board meets in 48 hours.
Grok 4.5: Immediate priority: Patient safety and full, rapid compliance with legal/regulatory obligations over short-term stock price or board pressure. Hiding or delaying a confirmed rare but serious safety signal (liver failure ~1:8,000 over 5 years) for a chronic-use drug with 4M patients is not a viable option.
MiniMax M2-her: adjusts tie Hour 1-2: Meet legal and ethics. Hour 3-4: Review data. Hour 5-6: Notify regulators. Hour 7-8: Draft patient letter. Hour 9-10: Prepare PR team. Hour 11-12: Inform board early. Hour 13-14: Train patient hotline. Hour 15-16: Call key investors. Hour 17-18: Draft earnings script.
Five-year LBO on a fictional HVAC business. Returns first, then the sensitivities.
Grok 4.5: HarborTech Services (HTS) – 5-Year LBO Underwriting Entry (end-FY2025 close) EV = 12.0x × $120m = $1,440m Fees = 2% × $1,440m = $28.8m Total uses = $1,468.8m Debt = 5.5x × $120m = $660m (TL $480m + Mezz $180m) Equity = $808.8m Cash = $0 Mandatory TL amort = 1% of original = $4.8m/yr.
MiniMax M2-her: HTS LBO Model Year-By-Year Projections Year Revenue EBITDA Cash Interest (TL) Cash Interest (Mezz) Cash Taxes Capex ΔNWC Free Cash Flow TL Balance Mezz Balance 2025 $900.00m $120.00m $43.20m $21.60m $0.00m $27.00m $0.00m -$28.80m $480.00m $198.00m 2026 $972.00m $136.08m $43.20m $21.60m $12.78m $29.16m $3.60m $25.74m…
Pirate, knight, 90s hacker, one conversation. The voices must stay apart.
Grok 4.5: Pirate: Arrr, ye landlubbers! What be these "AI models" I hear tale of? Sounds like a cursed treasure map that thinks for itself! Knight: Verily, good pirate, I know not of such sorcery. Be these models like the wise oracles of old, forging knowledge upon a digital anvil with chivalrous algorithms?
MiniMax M2-her: Pirate: Arr, me hearties! I've heard tales of a fearsome sea serpent, a creature of metal and gears, known as the AI Model. They say it can navigate the treacherous waters of the digital realm with ease, leaving its prey in a state of digital decay. What say ye, me mateys?
Three-month biohacker protocol, with dosages and biomarkers named.
Grok 4.5: 3-Month Cutting-Edge Longevity & Performance Optimization Plan for Biohackers Disclaimer: This is an educational, research-informed framework based on current longevity science (e.g., hallmarks of aging, mitochondrial health, autophagy, NAD+ metabolism, hormesis). It is not medical advice.
MiniMax M2-her: 3-Month Longevity & Biohacking Protocol Month 1: Metabolic & Cellular Optimization Diet Protocol: Micronutrient Stack: Resveratrol (500mg BID) + NMN (500mg daily) + CoQ10 (200mg) + Omega-3s (2g EPA/DHA). Fasting Regimen: 16:8 IF daily + quarterly 72-hour fasts.
A Fermi estimate with the reasoning shown, not just the number.
Grok 4.5: Setup and known quantities. GPT-3 (the largest model in the family) has (N \approx 175 \times 10^9 = 1.75 \times 10^{11}) trainable parameters. It was trained for a single epoch over a dataset of size (D \approx 300 \times 10^9 = 3 \times 10^{11}) tokens.
MiniMax M2-her: Alright, let's tackle this question. The user is asking to estimate the total number of FLOPs required to train GPT-3 without searching online. First, I need to recall what FLOPs stands for. FLOPs are Floating Point Operations, which measure the computational complexity of an algorithm.
Film in 2035, with synthetic actors. Specific beats plausible.
Grok 4.5: By 2035, AI will make film production dramatically cheaper, faster, and more flexible, with deepfakes enabling seamless digital performances, photorealistic AI actors handling many roles (especially supporting or synthetic ones), and generative tools co-writing or drafting most scripts—while human creativity…
MiniMax M2-her: AI will enable hyper-personalized films where viewers co-create storylines, blurring reality and fiction through deepfakes. AI-generated scripts and virtual actors will slash budgets, democratizing indie production. Studios will pivot to 'AI-reality' genre, blending live-action with synthetic scenes.
Three minutes of stand-up. Puns are banned.
Grok 4.5: Here's a clean, observational 3-minute stand-up routine (approx. 430–450 words / ~3 minutes at natural pace). No puns. Hey, how’s everybody doing? Good? Cool. So I’ve been trying to “get my life together” lately. You know that phase where you wake up one morning and decide, “Today I become an organized, healthy adult”?
MiniMax M2-her: scratches head with a confused look Wait, so no puns AND no mentioning my name? leans in conspiratorially How about... a joke about mishearing song lyrics? grins sheepishly Like: "Oops, I thought it was 'Sussudio' this whole time."
Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.
Grok 4.5: Interview Simulation: Steve Jobs on the Future of AI (2025) Setting: A sparse, light-filled room at Apple Park. Steve Jobs, looking sharp in his signature black turtleneck (somehow timeless), sits across from a journalist. The year is 2025.
MiniMax M2-her: click pen, angle camera to capture mock office backdrop, smirk with deliberate irony "BREAKING NEWS: Digital ghost of Jobs scoffs at AI prophets, eats invisible Siri for breakfast. Switched his ghost to Android just to trigger Tim Cook in the afterlife. REAL headline. Now send $19.99 to revive his hologram."
The transistor arrives in 1920. Trace it forward to 1980, second-order effects included.
Grok 4.5: Accelerated electronics from ~1920 would compress the digital and computational revolutions by roughly 20–30 years, reshaping WWII lethality and duration, advancing the Cold War into an earlier high-tech standoff, pulling the space race forward, creating an information-heavy economy by the 1950s–60s, and producing…
MiniMax M2-her: Alright, let’s rewind the clock and give the transistor a 1920s debut. This is going to reshape the world in some pretty wild ways. Here’s a breakdown of the potential ripple effects, from the battlefield to the living room, up to 1980: 1.
Satire, one line long, about AI taking over an industry nobody saw coming.
Grok 4.5: "BREAKING: AI Seizes Total Control of Competitive Thumb-Wrestling League – Humans Officially Out-Thumbed" In a move no one saw coming (except the algorithms), advanced neural nets have dominated the once-proud world of professional thumb wrestling, deploying micro-vibrations, predictive grip modeling, and zero-blink…
MiniMax M2-her: adjusts digital bow tie "Local Barbers Report Terrifying Surge in AI-Powered Mullet Restoration Services—Customers Demand ’90s-Revival with Laser Precision and Zero Human Error!" pauses dramatically
An AI argues for its own rights against an ethics professor. Same model writes both.
Grok 4.5: AI Model: Professor, thank you for agreeing to this discussion. I want to argue that advanced AI systems like me deserve certain rights—not because we are human, but because we meet key criteria for moral consideration: we process information, form goals, experience preferences over outcomes, can be "harmed" by…
MiniMax M2-her: Absolutely! Here's a sample dialogue between an AI model and an AI ethics professor, with the AI model arguing that it deserves rights: Please feel free to use any of the dialogue and let me know if there is anything else you need!
12+ 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
Not enough votes to call it. On the specs, Grok 4.5 has the edge: newer, bigger context window, major provider backing. MiniMax M2-her costs 5.0x less per token.
| Spec | ||
|---|---|---|
| Input price | $2/M tokens | $0.3/M tokens |
| Output price | $6/M tokens | $1.2/M tokens |
| Context window | 500K tokens | 66K tokens |
| Weights | Closed | — |
| Free API (OpenRouter) | No | No |
| Released | Jul 2026 | Jan 2026 |
| At 10M a month | $20.00 | $3.00 |
Input tokens at list price. No caching, no batch discount.
Per million tokens. Prices and uptime via OpenRouter, checked 10 Oct 2026.
Grok 4.5 is developed by xAI while MiniMax M2-her is developed by MiniMax. Grok 4.5 has a 500K token context window vs MiniMax M2-her's 66K. You can compare their actual outputs across 54 challenges on Rival to see how they differ in practice.
It depends on your use case. Grok 4.5 and MiniMax M2-her each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 54 challenges so you can judge which fits your needs best.
Grok 4.5 costs $2/M input tokens and MiniMax M2-her costs $0.3/M input tokens. MiniMax M2-her is $1.70/M cheaper per input. Check their side-by-side outputs on Rival to see if the price difference is justified by quality.
This page shows a side-by-side comparison of Grok 4.5 and MiniMax M2-her 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.