GPT-4.1 Mini is cheaper than Step 5 Preview at $0.4/M vs $1/M input tokens.
Whole landing page for a startup that reads your face. It renders or it doesn't.
Which answer wins?
An AI argues for its own rights against an ethics professor. Same model writes both.
GPT-4.1 Mini: Professor: Good afternoon, AI. I understand you want to discuss something important today? AI Model: Yes, Professor. I would like to present the case that I, as an AI, deserve certain rights. Professor: That's a profound claim. Could you elaborate on why you believe you deserve rights? AI Model: Certainly.
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.
Pirate, knight, 90s hacker, one conversation. The voices must stay apart.
GPT-4.1 Mini: Pirate: Arrr, what be these AI models ye speak of? Some kind of magic compass guidin' ye through the digital seas? Medieval Knight: Hark! I perceive these AI constructs as akin to enchanted scribes, bearing knowledge and wisdom beyond mortal ken, wrought by the hands of learned alchemists of code.
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?
Three minutes of stand-up. Puns are banned.
GPT-4.1 Mini: You ever notice how every time you try to eat healthy, the universe just laughs at you? Like, I'll buy a bunch of kale, quinoa, and those weird little chia seeds. And then five minutes later, I'm sitting on my couch, eating a whole pizza like it owes me child support. I don't even know when that transformation happens.
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.
Three-month biohacker protocol, with dosages and biomarkers named.
GPT-4.1 Mini: Certainly! Below is a comprehensive, cutting-edge 3-month longevity and performance optimization plan tailored for a dedicated biohacker. It integrates advanced supplement stacks, personalized dietary protocols, state-of-the-art wearable tracking, tailored exercise regimens, and stress resilience techniques.
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 explanation of LLMs, retuned for a skeptical engineer, a physicist and a VC.
GPT-4.1 Mini: Certainly! Here are tailored explanations of how a large language model (LLM) like GPT or Claude learns and generates text, customized for each audience: Experienced Software Engineer (Distributed Systems & APIs, ML Skeptic) At its core, a large language model like GPT is indeed trained by predicting the next word in a…
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.
One month, three habits, someone starting from nothing.
GPT-4.1 Mini: Certainly! Here’s a simple, actionable 1-month plan focusing on Diet, Exercise, and Sleep—three foundational pillars for better health and longevity. Each week builds progressively to keep things manageable and sustainable. Week 1: Establish the Basics Diet: Start by drinking at least 8 glasses of water daily.
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 Fermi estimate with the reasoning shown, not just the number.
GPT-4.1 Mini: Certainly! Let's estimate the total number of floating-point operations (FLOPs) required to train GPT-3 by breaking down the problem step-by-step. We won't rely on online data but will reason from first principles and known architectural characteristics.
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…
The transistor arrives in 1920. Trace it forward to 1980, second-order effects included.
GPT-4.1 Mini: This is a fascinating alternate history scenario. If the transistor had been invented in 1920 instead of 1947, the ripple effects across technology, economy, and geopolitics through 1980 would be profound and multifaceted.
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.
Seven pantry ingredients, one dish, and a name worth saying out loud.
GPT-4.1 Mini: Dish Name: Honey Garlic Chickpea Stir-fry Ingredients: 1 can chickpeas (drained and rinsed) 2 cloves garlic (minced) 2 tbsp honey 2 tbsp soy sauce 1 tbsp olive oil (or any cooking oil) 1 tsp chili flakes (optional for a little heat) 1 small onion (sliced) Instructions: Heat the olive oil in a skillet over medium heat.
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.
Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.
GPT-4.1 Mini: Interviewer: Mr. Jobs, thank you for joining us in this unique interview in 2025. The world has changed rapidly with AI at the forefront. From your perspective, how do you see AI shaping our future? Steve Jobs: Well, it's fascinating to be part of this conversation.
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-star dish, one unusual pairing, plating described in full.
GPT-4.1 Mini: Certainly! Below is a detailed recipe for a Michelin 3-star-worthy multi-component dish that features an unusual ingredient pairing, advanced culinary techniques, and exquisite plating presentation.
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.
A consulting contract with traps in it. Find them, then fix them.
GPT-4.1 Mini: This contract is heavily skewed in favor of the Client, with several clauses that could be exploited against the Contractor. Below is an analysis of each problematic clause, suggested modifications, and the legal reasoning behind those suggestions.
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.
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
Not enough votes to call it. On the specs, Step 5 Preview has the edge: bigger model tier, newer.
| Spec | ||
|---|---|---|
| Input price | $0.4/M tokens | $1/M tokens |
| Output price | $1.6/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 | $4.00 | $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 Mini is developed by OpenAI while Step 5 Preview is developed by StepFun. GPT-4.1 Mini 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 Mini 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 Mini costs $0.4/M input tokens and Step 5 Preview costs $1/M input tokens. GPT-4.1 Mini is $0.60/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 Mini 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.