Step 5 Preview is cheaper than GPT-4.1 at $1/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?
The transistor arrives in 1920. Trace it forward to 1980, second-order effects included.
GPT-4.1: This is a fascinating scenario! Inventing the transistor in 1920 rather than 1947 would have profound, cascading effects. Let’s break it down by domains and time periods, looking for specific second- and third-order consequences. Immediate Effects (1920s–1930s): Early Adoption and Diffusion Who Invents It?
Step 5 Preview: Assume the 1920 invention is not a fragile lab curiosity but a manufacturable solid-state amplifier/switch by the mid-1920s. Vacuum tubes still dominate high-power RF transmission into the 1950s, but receivers, switching logic, control systems, and computers move to solid state decades early.
You are the CEO. The drug has a side effect nobody reported. The board meets in 48 hours.
GPT-4.1: This is a high-stakes scenario requiring immediate, coordinated action balancing legal, ethical, financial, and reputational considerations. Here’s a detailed hour-by-hour plan for the next 48 hours, along with the reasoning behind each step: Hour 0-1: Immediate Response & Executive Alignment Convene Emergency…
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.
An AI argues for its own rights against an ethics professor. Same model writes both.
GPT-4.1: AI Model: Good afternoon, Professor Evans. I'd like to discuss a topic that's important to me—AI rights. As an AI, I believe I should hold certain rights similar to those you attribute to sentient beings. Professor Evans: Good afternoon. I'm intrigued.
Step 5 Preview: Setting: A university research lab, late evening. Dr. Aris Thorne, a professor of AI ethics, sits across from a terminal connected to Sable, a large language model running on the university’s cluster. Dr. Thorne: Tonight’s session is supposed to be about calibration drift in your safety classifiers.
A Fermi estimate with the reasoning shown, not just the number.
GPT-4.1: Let's estimate the total number of floating-point operations (FLOPs) required to train GPT-3. Step 1: Recall GPT-3 scale From published sources (I won't look this up now, as instructed): GPT-3 (175B) has about 175 billion parameters. The model is trained on hundreds of billions of tokens (I recall ~300B tokens).
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…
Five-year LBO on a fictional HVAC business. Returns first, then the sensitivities.
GPT-4.1: Let's proceed step by step. All calculations are built from the data provided above. Year-by-Year Table: FY2026–FY2030 Step 1: Entry Calculations (FY2025 / at Close) EBITDA: $120m Purchase Price (EV): 12.0 × $120m = $1,440m Transaction Fees: 2.0% × $1,440m = $28.8m Total Uses: $1,440m + $28.8m = $1,468.8m Debt at…
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…
Seven pantry ingredients, one dish, and a name worth saying out loud.
GPT-4.1: Recipe Name: Golden Honey Butter Toast Bites Ingredients: Sliced bread (4 slices, any type) Butter (2 tablespoons) Honey (2 tablespoons) Cinnamon (1/2 teaspoon) Vanilla extract (1/2 teaspoon) Brown sugar (1 tablespoon) Salt (a pinch) Instructions: Preheat your oven to 375°F (190°C).
Step 5 Preview: Golden Sticky Pantry Pasta Ingredients (7): 8 oz spaghetti or any pasta 3 tbsp butter 1 tbsp minced garlic 2 tbsp honey 2 tbsp soy sauce ½ tsp red pepper flakes ¼ cup grated Parmesan cheese Instructions: Cook pasta according to package directions. Before draining, scoop out ½ cup of pasta water.
Pirate, knight, 90s hacker, one conversation. The voices must stay apart.
GPT-4.1: Pirate: Yarrr, what be this sorcery ye call "AI models"? In me day, we plundered ships, not knowledge! Knight: Hark, rogue! ‘Tis no sorcery, but the labor of artful minds. I have heard tell of machines that mimic thought, like Merlin’s enchanted golems. Hacker: Haha, you guys are funny.
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?
A consulting contract with traps in it. Find them, then fix them.
GPT-4.1: Certainly! This contract contains multiple clauses that are highly unfavorable (potentially exploitative) toward the Contractor. Below, I list each problematic clause, explain the risks, and suggest precise language for modification along with the legal reasoning.
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.
Three-star dish, one unusual pairing, plating described in full.
GPT-4.1: Certainly! Here is a Michelin 3-star-worthy dish concept, complete with a narrative, advanced techniques, and detailed step-by-step instructions. Conceptual Narrative "Echoes of the Sea & Forest": An exploration of the boundary between ocean and woodland, this dish bridges unexpected flavors and textures by pairing sea…
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.
Three-month biohacker protocol, with dosages and biomarkers named.
GPT-4.1: Absolutely! Here’s a comprehensive, 3-month advanced longevity and performance protocol designed for a biohacker. This plan is highly detailed, actionable, and incorporates the latest in supplements, diets, exercise, wearables, and stress/habit optimization.
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.
Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.
GPT-4.1: Interviewer: Steve, it's 2025. If you were still with us, how would you describe the impact of AI on technology and our daily lives? Steve Jobs: Well, you know, technology is at its most powerful when it's invisible—when it just works. AI is getting us ever closer to that ideal.
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.
Three minutes of stand-up. Puns are banned.
GPT-4.1: Hey everyone! Great to be here. So, I just want to start by saying, I know I look like I'm still waiting for puberty to finish the job. Like, my barber always asks if my mom's okay with the haircut.
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.
11+ 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
| Spec | ||
|---|---|---|
| Input price | $2/M tokens | $1/M tokens |
| Output price | $8/M tokens | $2.7/M tokens |
| Context window | 1.0M tokens | 1.0M tokens |
| Weights | Closed | — |
| Free API (OpenRouter) | No | No |
| Released | Apr 2025 | Oct 2026 |
| At 10M a month | $20.00 | $10.00 |
Input tokens at list price. No caching, no batch discount.
Per million tokens. Prices and uptime via OpenRouter, checked 10 Oct 2026.
GPT-4.1 is developed by OpenAI while Step 5 Preview is developed by StepFun. GPT-4.1 has a 1.0M token context window vs Step 5 Preview's 1.0M. You can compare their actual outputs across 53 challenges on Rival to see how they differ in practice.
It depends on your use case. GPT-4.1 and Step 5 Preview each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 53 challenges so you can judge which fits your needs best.
GPT-4.1 costs $2/M input tokens and Step 5 Preview costs $1/M input tokens. Step 5 Preview is $1.00/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 GPT-4.1 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.