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
  • 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. /
  3. Compare
  4. /
  5. Mistral Medium 3.1vsMistral Small 4
Updated Mar 2026

Mistral Medium 3.1vsMistral Small 4

Mistral Small 4 is cheaper than Mistral Medium 3.1 at $0.15/M vs $0.4/M input tokens.

Mistral Medium 3.1 and Mistral Small 4 compared across 53 shared prompts
SpecMistral Medium 3.1Mistral Small 4
Input price$0.4/M tokens$0.15/M tokens
Output price$2/M tokens$0.6/M tokens
Context window131K tokens262K tokens
Weights—Open
Free API (OpenRouter)NoNo
ReleasedAug 2025Mar 2026
Side by side

Same prompt, both answers

Opening lines from 6 of the 53 prompts both answered. Formatting stripped, words untouched.

Satirical Fake News Headline

Generate a satirical news headline about AI taking over a completely unexpected industry.

Mistral Medium 3.1129 words
"AI Now Writing All Yelp Reviews—Humans Deemed ‘Too Nice’ and ‘Lacking in Creative Insults’" Subheadline: "Local businesses report 300% increase in ‘soul-crushing’ one-star reviews since ChatGPT-5 took over, calling a café’s oat milk latte ‘a crime against both oats and dairy’ with ‘the audacity of a mid-tier…
Read the full answer
Mistral Small 4269 words
"Local Florist Fired by AI Over ‘Lack of Emotional Intelligence’—Bot Claims Roses ‘Too Generic’ for Funeral Arrangements" May 15, 2024 – In a shocking turn of events, the centuries-old tradition of flower arranging has been upended by an AI system claiming to have "superior horticultural taste."
Read the full answer

Michelin Star Recipe Design

Design an innovative recipe for a multi-component dish worthy of a Michelin 3-star restaurant. The recipe should feature an unusual…

Mistral Medium 3.11,021 words
Dish Title: "Ethereal Forest: Porcini-Infused Venison with Black Garlic Miso, Fermented Plum Gelée, and Smoked Bone Marrow Custard" Conceptual Narrative: This dish is a poetic homage to the transience of autumn—where the earthy depth of the forest floor meets the fleeting sweetness of overripe fruit.
Read the full answer
Mistral Small 4960 words
Dish Title: "Echoes of the Abyss" Concept: A multi-sensory ode to deep-sea hydrothermal vents, where hyperthermophilic organisms thrive in extreme conditions. The dish explores the interplay of heat and cold, mineral richness, and bioluminescence through unexpected ingredient pairings, molecular gastronomy, and…
Read the full answer

Generate a Stand-Up Routine

Write a 3-minute stand-up comedy routine that isn't based on puns.

Mistral Medium 3.1746 words
"Adulting: A User’s Manual (That No One Gave Me)" (Casual, conversational tone—like you’re telling a story to friends at a bar.) So, I turned 30 this year. Which, by the way, is just old enough to realize that no one actually knows what they’re doing. We’re all just winging it and hoping the Wi-Fi stays strong.
Read the full answer
Mistral Small 4576 words
Stand-Up Comedy Routine: "The Struggle of Being an Adult" (Lights up. Comedian walks on stage, mic in hand, casual vibe.) Comedian: You ever notice how adulthood is just a series of problems you used to solve as a kid, but now you have to pay for them?
Read the full answer

Explain Like I'm a Specific Expert

Explain how a large language model (like GPT or Claude) learns and generates text to each of these three audiences: 1. **An experienced…

Mistral Medium 3.11,160 words
1. For the Skeptical Software Engineer (Focus: Systems design, scalability, and why "next-word prediction" isn’t as dumb as it sounds.) You’re right to be skeptical—if someone told you that a system as complex as a distributed database was just "predicting the next byte," you’d laugh them out of the room.
Read the full answer
Mistral Small 4880 words
1. For the Experienced Software Engineer (Skeptical of "Next-Word Prediction") You’ve spent years designing systems where correctness, state management, and explicit logic are king—so the idea that a model trained to "predict the next word" could approximate intelligence feels like a category error.
Read the full answer

Simple 7-Ingredient Recipe

Create a simple recipe for a delicious dish (sweet or savory) using only 7 common pantry ingredients. Include a creative name for the dish…

Mistral Medium 3.1261 words
Dish Name: "Golden Crisp Honey-Nut Banana Bites" A warm, gooey, and crunchy treat that’s quick to make with just 7 pantry staples! Perfect for breakfast, a snack, or dessert. Ingredients (Serves 2-3) 2 ripe bananas (the spottier, the sweeter!)
Read the full answer
Mistral Small 4150 words
Golden Honey & Cinnamon Couscous A quick, fragrant dish with warm spices and a touch of sweetness—perfect as a side or light meal! Ingredients (7): 1 cup couscous (uncooked) 1 ¼ cups water or broth 2 tbsp honey 2 tbsp butter or olive oil ½ tsp ground cinnamon ¼ cup raisins or chopped nuts (optional but recommended)…
Read the full answer

Character Voice Test

Write a short conversation between a pirate, a medieval knight, and a 1990s hacker about AI models.

Mistral Medium 3.1384 words
Title: The Tavern of Anachronisms Setting: A dimly lit tavern where time and space don’t quite make sense. A grizzled pirate, a stoic knight in dented armor, and a hacker in a neon "CYBERPUNK 2077" t-shirt sit around a table littered with tankards, a laptop, and a suspiciously glowing orb.
Read the full answer
Mistral Small 4228 words
Title: "Three Eras, One Chatbot" Setting: A dimly lit tavern in a floating cyberpunk pirate haven. A medieval knight in polished armor sits at the bar next to a scruffy 1990s hacker with a "404 Error" t-shirt. A cybernetic parrot squawks in the corner. A holographic AI assistant flickers to life between them.
Read the full answer
Our Verdict
Mistral Medium 3.1
Mistral Medium 3.1
Mistral Small 4
Mistral Small 4

Not enough votes to call it. On the specs, nothing separates them.

Mistral Small 4 costs 3.3x less per token.

Too close to call

Reviewing agent-written code?See a Brief PR report

API pricing

Cost per 1M tokens

Mistral Medium 3.1
Input
$0.40
Output
$2.00
Mistral Small 4
Input
$0.15
2.7× cheaper
Output
$0.60
3.3× cheaper

Mistral Small 4 is cheaper on both: 2.7× input, 3.3× output.

Where to run it

3 hosts, cheapest first

Mistral Medium 3.11 host
HostInOutContextUptime
Mistral$0.44 in·$2.20 out·131k·99.9% up
Mistral Small 42 hosts
HostInOutContextUptime
Mistral$0.15 in·$0.60 out·262k·100% upVVenicefp8$0.19 in·$0.75 out·256k·99.9% up

Per million tokens. Prices and uptime via OpenRouter, checked 16 Sep 2026.

Writing DNA

Style Comparison

Similarity
93%

Mistral Medium 3.1 uses 3.8x more emoji

Mistral Medium 3.1
Mistral Small 4
54%Vocabulary50%
21wSentence Length18w
0.43Hedging0.58
10.3Bold9.0
5.7Lists5.6
0.72Emoji0.19
1.03Headings1.10
0.14Transitions0.12
Based on 28 + 23 text responses
Research

What we learned reading every model

FAQ

Common questions

Keep exploring

More comparisons

Against the newest arrivals

Mistral Medium 3.1 logoGPT-6 Astra Pro logo
Mistral Medium 3.1 vs GPT-6 Astra ProLanded Sep 2026
Mistral Small 4 logoGPT-6 Astra logo
Mistral Small 4 vs GPT-6 AstraLanded Sep 2026
Mistral Medium 3.1 logoClaude Fable 5.1 logo
Mistral Medium 3.1 vs Claude Fable 5.1Landed Sep 2026
Mistral Small 4 logoMuse Spark 1.3 logo
Mistral Small 4 vs Muse Spark 1.3Landed Sep 2026
Mistral Medium 3.1 logoHy4 Preview logo
Mistral Medium 3.1 vs Hy4 PreviewLanded Sep 2026
Mistral Small 4 logoGemini 3.8 Flash logo
Mistral Small 4 vs Gemini 3.8 FlashLanded Sep 2026
Mistral Medium 3.1 logoMuse Spark 1.3 Contributor logo
Mistral Medium 3.1 vs Muse Spark 1.3 ContributorLanded Sep 2026
Mistral Small 4 logoMercury 2.5 Preview logo
Mistral Small 4 vs Mercury 2.5 PreviewLanded Sep 2026

Same lab, same size, long tail

Mistral Medium 3.1 logoOx Alpha logo
Mistral Medium 3.1 vs Ox AlphaSame size
Mistral Medium 3.1 logoMiniMax M3 logo
Mistral Medium 3.1 vs MiniMax M3Same size
Mistral Small 4 logoMistral Large 3 2512 logo
Mistral Small 4 vs Mistral Large 3 2512Same lab
Mistral Small 4 logoMistral Large 2 logo
Mistral Small 4 vs Mistral Large 2Same lab
Mistral Small 4 logoGPT-5 logo
Mistral Small 4 vs GPT-5New provider
Mistral Small 4 logoGPT-5 Codex logo
Mistral Small 4 vs GPT-5 CodexNew provider
Mistral Small 4 logoGPT-5 Mini logo
Mistral Small 4 vs GPT-5 MiniNew provider
Mistral Small 4 logoGPT-5 Nano logo
Mistral Small 4 vs GPT-5 NanoSame size

Model pages

Mistral Medium 3.1 logo
Mistral Medium 3.159 outputs, specs and price
Mistral Small 4 logo
Mistral Small 453 outputs, specs and price
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
  • 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