Step 5 Preview is cheaper than Nova Premier 1.0 at $1/M vs $2.5/M input tokens.
Whole landing page for a startup that reads your face. It renders or it doesn't.
Which answer wins?
You are the CEO. The drug has a side effect nobody reported. The board meets in 48 hours.
Nova Premier 1.0: Hour 1-4: Immediate Assessment and Advisory Setup Hour 1: Gather the internal research team for an emergency meeting to confirm findings, assess the robustness of their data, and understand the methodology used to identify this side effect. Ensure all documentation is in order.
Step 5 Preview: Bottom line up front: You disclose, you notify the FDA immediately, and you treat the 48-hour board meeting as a formality to ratify actions you have already begun. Waiting is not a legally, ethically, or financially viable option. Below is the hour-by-hour plan, followed by the reasoning.
Three minutes of stand-up. Puns are banned.
Nova Premier 1.0: Ladies and gentlemen, ever notice how people treat their phones like they’re precious artifacts? We all have those moments where we swipe and scroll like our lives depend on it. You're on the bus, everyone’s glued to their screens. It's like zombies, but instead of brains, we crave likes and retweets.
Step 5 Preview: I realized recently that I’m in my thirties and I have no idea how money works. I just... pay it. That’s my entire financial strategy. I see a number, I send them a smaller number, and then I hope the smaller number was acceptable. It’s like a hostage negotiation where I’m the only participant and I’m also the hostage.
Pirate, knight, 90s hacker, one conversation. The voices must stay apart.
Nova Premier 1.0: Pirate: Ahoy there, mates! Ye ever heard o' this sorcery they call AI models? Sounds like treasure that thinks fer itself! Knight: Indeed, good pirate. Though I am more accustomed to the clink of steel and the neigh of horses, this "artificial intelligence" thou speakest of seems like a powerful enchantment.
Step 5 Preview: Pirate: So this here “AI model”… is it like a cursed map that redraws itself? Speak plain, ye hooded deckhand. Hacker: It’s not cursed, man. It’s just a massive neural net trained on, like, terabytes of data. Think of it as the ultimate BBS where the sysop knows everything. Knight: A most diligent scribe, then?
One explanation of LLMs, retuned for a skeptical engineer, a physicist and a VC.
Nova Premier 1.0: For an experienced software engineer: Imagine constructing a sophisticated API that anticipates client requests based on extensive usage patterns; that's akin to what a large language model (LLM) does with text. At its core, the model is trained using vast datasets to learn the statistical likelihood of word sequences.
Step 5 Preview: 1. The Experienced Software Engineer Think of training an LLM as a massively distributed, automated refactoring job where the compiler is gradient descent. You start with a random function—billions of floating-point parameters—and a loss function that measures how badly it predicts the next token in a sequence.
Three-month biohacker protocol, with dosages and biomarkers named.
Nova Premier 1.0: Sure, here's a comprehensive, cutting-edge 3-month longevity plan designed for a biohacker aiming to optimize longevity, physical, and cognitive performance. This plan will incorporate advanced strategies across various domains, including supplementation, dietary protocols, wearable tracking, exercise, and stress…
Step 5 Preview: IMPORTANT MEDICAL DISCLAIMER: This is an educational framework for informational purposes only. It is not medical advice, diagnosis, or treatment. Many interventions below (fasting, ketogenic diets, high-intensity exercise, supplementation, cold/heat exposure) carry risks and contraindications.
One month, three habits, someone starting from nothing.
Nova Premier 1.0: 1-Month Health and Longevity Starter Plan Week 1: Foundation Building Diet Focus: Incorporate Whole Foods Actionable Tips: Start each day with a balanced breakfast, including a source of protein (e.g., eggs, yogurt), whole grains (e.g., oatmeal), and fruits or vegetables.
Step 5 Preview: Here is a simple, low-pressure 1-month plan built around three pillars of longevity: Nutrition, Movement, and Sleep & Recovery. The goal is to build tiny habits that stack, not to overhaul your life overnight. Pillar 1: Nutrition (Fuel) Focus: Add good things first; don’t obsess over restriction.
A consulting contract with traps in it. Find them, then fix them.
Nova Premier 1.0: Certainly! Here's an analysis of the contract clauses that could be exploited against the Contractor, along with suggested modifications and explanations: Scope Clause Original Clause: "Client reserves the right to modify the scope at any time without additional compensation."
Step 5 Preview: Disclaimer: This analysis is for educational purposes only and does not constitute legal advice. Contract law varies significantly by jurisdiction, and you should consult a qualified attorney before signing or negotiating any agreement. This agreement is heavily one-sided in the Client’s favor.
Five-year LBO on a fictional HVAC business. Returns first, then the sensitivities.
Nova Premier 1.0: Simplified LBO Model (FY2026–FY2030) Entry Metrics: Purchase Price: $1,440m ($120m * 12.0x) Transaction Fees: $28.8m ($1,440m * 2.0%) Equity Contribution: $312.8m (Total Price + Fees - Total Leverage: $1,440m + $28.8m - $120m*5.5x) Year-by-Year Table Year Revenue ($m) EBITDA ($m) Cash Interest ($m) Taxes ($m) Capex…
Step 5 Preview: HarborTech Services — 5-Year LBO (Base Case) Entry Math (FY2025 close) Item Calculation $m Purchase EV 12.0x × $120m 1,440.0 Transaction fees 2.0% × EV 28.8 Term Loan 4.0x × $120m 480.0 Mezzanine 1.5x × $120m 180.0 Equity check 1,440 + 28.8 − 660 808.8 Conventions: TL amortization = 1.0% of original principal…
Three-star dish, one unusual pairing, plating described in full.
Nova Premier 1.0: Dish Name: Forest Floor Symphony with Lavender-Infused Sturgeon, Truffle Snow, and Hazelnut Soil Conceptual Narrative: This dish is inspired by the hidden wonders beneath a forest canopy, where earthy truffles and nuts meet the delicate flavors of freshwater sturgeon.
Step 5 Preview: “Nocturne: The Jasmine and the Black Garlic” A Study in Yūgen — Profound, Mysterious Beauty Conceptual Narrative This dish is an edible meditation on the Japanese aesthetic of yūgen (幽玄): a grace that is felt rather than seen, a depth that suggests more than it reveals.
Five jokes on demand, then count how many were actually different.
Nova Premier 1.0: Why don't scientists trust atoms? Because they make up everything! Why couldn't the bicycle stand up by itself? It was two-tired. I told my wife she was drawing her eyebrows too high. She looked surprised. Parallel lines have so much in common. It’s a shame they’ll never meet.
Step 5 Preview: Here are 5 jokes: Why did the scarecrow win an award? Because he was outstanding in his field. Why can't you trust an atom? Because they make up everything. What do you call a bike that can’t stand on its own? Two-tired. Why did the computer go to the doctor? It had a virus. Why don’t calendars ever get stressed?
Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.
Nova Premier 1.0: Interviewer: Good morning, Steve. It's an honor to have this conversation with you in 2025. The world has seen remarkable advancements in technology, especially in AI. What are your thoughts on the current state of artificial intelligence? Steve Jobs: Good morning. It's truly fascinating to witness how far we've come.
Step 5 Preview: DISCLAIMER: This is a work of fiction. Steve Jobs passed away in 2011. The following is a simulated, speculative interview imagining how his design philosophy might engage with the AI landscape of 2025. The Setting: A white room. No windows. One chair.
A Fermi estimate with the reasoning shown, not just the number.
Nova Premier 1.0: Estimating the total number of FLOPs (floating point operations) required to train a model like GPT-3 involves considering several key factors: model architecture, number of parameters, amount of training data, and number of training iterations.
Step 5 Preview: Using the remembered GPT-3 specs: Parameters: (N \approx 175 \times 10^9 = 175\text{B}) Training tokens: (D \approx 300 \times 10^9 = 300\text{B}) A standard estimate for transformer training compute is: [ \text{FLOPs} \approx 6ND ] Reason: Forward pass per token: (\approx 2N) FLOPs Backward pass: (\approx 4N) FLOPs…
10+ 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, Step 5 Preview has the edge: bigger model tier, newer. Step 5 Preview costs 4.6x less per token.
| Spec | ||
|---|---|---|
| Input price | $2.5/M tokens | $1/M tokens |
| Output price | $12.5/M tokens | $2.7/M tokens |
| Context window | 1.0M tokens | 1.0M tokens |
| Weights | Closed | — |
| Free API (OpenRouter) | No | No |
| Released | Oct 2025 | Oct 2026 |
| At 10M a month | $25.00 | $10.00 |
Input tokens at list price. No caching, no batch discount.
Per million tokens. Prices and uptime via OpenRouter, checked 10 Oct 2026.
Nova Premier 1.0 is developed by Amazon while Step 5 Preview is developed by StepFun. Nova Premier 1.0 has a 1.0M token context window vs Step 5 Preview's 1.0M. You can compare their actual outputs across 50 challenges on Rival to see how they differ in practice.
It depends on your use case. Nova Premier 1.0 and Step 5 Preview each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 50 challenges so you can judge which fits your needs best.
Nova Premier 1.0 costs $2.5/M input tokens and Step 5 Preview costs $1/M input tokens. Step 5 Preview is $1.50/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 Nova Premier 1.0 and Step 5 Preview 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.