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
  • Default Index
  • 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. GPT-5.1-Codex-MinivsMercury 2.5
Updated Sep 2026

GPT-5.1-Codex-MinivsMercury 2.5

Mercury 2.5 is cheaper than GPT-5.1-Codex-Mini at $0.04/M vs $1.5/M input tokens.

GPT-5.1-Codex-Mini and Mercury 2.5 compared across 20 shared prompts
SpecGPT-5.1-Codex-MiniMercury 2.5
Input price$1.5/M tokens$0.04/M tokens
Output price$6/M tokens$0.15/M tokens
Context window400K tokens260K tokens
WeightsClosed—
Free API (OpenRouter)NoNo
ReleasedNov 2025Sep 2026
Side by side

Same prompt, both answers

Opening lines from 3 of the 20 prompts both answered. Formatting stripped, words untouched.

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…

GPT-5.1-Codex-Mini182 words
Honey-Garlic Chickpea Sizzle Bowls Prep + Cook Time: ~25 minutes Ingredients (7 pantry staples): 1 can chickpeas, drained and rinsed 1 cup rice (white or brown) 2 tbsp olive oil 3 garlic cloves, minced (or 1 tsp garlic powder if canned) 2 tbsp honey 2 tbsp soy sauce 1/2 tsp chili flakes (adjust to your heat preference)…
Read the full answer
Mercury 2.5190 words
Pantry Pasta Primavera Prep Time: 5 minutes Cook Time: 15 minutes Servings: 2 Ingredients (7 Common Pantry Items) Pasta (spaghetti, penne, or fusilli) – 8 oz Canned crushed tomatoes – 1 can (14 oz) Olive oil – 3 tablespoons Garlic powder – 1 teaspoon Dried oregano – 1 teaspoon Parmesan cheese (grated) – ½ cup Salt and…
Read the full answer

Mini LBO Underwrite

You are underwriting a 5-year LBO for a private equity investment committee. Company (fictional): HarborTech Services (HTS) –…

GPT-5.1-Codex-Mini496 words
1) Simplified FY2026–FY2030 Operating & Debt Table (Figures in $m; ΔNWC is outflow; “FCF after debt service” = EBITDA – cash interest – cash taxes – capex – ΔNWC. Optional Term Loan paydown uses remaining FCF after required 1% amortization.)
Read the full answer
Mercury 2.5403 words
1. Simplified Year-by-Year LBO Model (FY2026–FY2030) Entry Assumptions: Enterprise Value (EV): $120m × 12.0x = $1,440m Transaction Fees: $1,440m × 2.0% = $28.8m Total Debt at Close: $120m × 5.5x = $660m Term Loan: $120m × 4.0x = $480m Mezzanine: $120m × 1.5x = $180m Equity Required: $1,440m (EV) + $28.8m (Fees) − $660m…
Read the full answer

Beginner's Longevity Plan

Outline a simple, actionable 1-month plan for someone starting their journey towards better health and longevity. Focus on 3 key areas…

GPT-5.1-Codex-Mini577 words
1-Month Beginner Plan for Better Health & Longevity Focus areas: Nutrition, Movement, and Sleep & Stress Balance. Each week builds a little habit-building momentum. Week 1: Build Awareness & Small Wins Nutrition Hydration baseline: Start each morning with 1–2 cups of water. Carry a bottle.
Read the full answer
Mercury 2.5325 words
Here is a simple, actionable 1-month plan to kickstart your journey toward better health and longevity. This guide focuses on three foundational pillars: Nutrition, Movement, and Sleep. Week 1: Awareness & Small Wins Goal: Build habits without overwhelming yourself.
Read the full answer
Our Verdict
GPT-5.1-Codex-Mini
GPT-5.1-Codex-Mini
Mercury 2.5
Mercury 2.5Runner-up

Not enough votes to call it. On the specs, GPT-5.1-Codex-Mini has the edge: bigger model tier, bigger context window, major provider backing.

Mercury 2.5 costs 40x less per token.

Too close to call

Reviewing agent-written code?See a Brief PR report

API pricing

Cost per 1M tokens

GPT-5.1-Codex-Mini
Input
$1.50
Output
$6.00
Mercury 2.5
Input
$0.04
38× cheaper
Output
$0.15
40× cheaper

Mercury 2.5 is cheaper on both: 38× input, 40× output.

Where to run it

2 hosts

GPT-5.1-Codex-Mini1 host
HostInOutContextUptime
Azure AI Foundry$0.25 in·$2.00 out·400k·100% up
Mercury 2.51 host
HostInOutContextUptime
Inception$0.04 in·$0.15 out·260k·100% up

Per million tokens. Prices and uptime via OpenRouter, checked 23 Sep 2026.

Research

What we learned reading every model

FAQ

Common questions

GPT-5.1-Codex-Mini is developed by OpenAI while Mercury 2.5 is developed by Inception. GPT-5.1-Codex-Mini has a 400K token context window vs Mercury 2.5's 260K. You can compare their actual outputs across 20 challenges on Rival to see how they differ in practice.

It depends on your use case. GPT-5.1-Codex-Mini and Mercury 2.5 each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 20 challenges so you can judge which fits your needs best.

GPT-5.1-Codex-Mini costs $1.5/M input tokens and Mercury 2.5 costs $0.04/M input tokens. Mercury 2.5 is $1.46/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-5.1-Codex-Mini and Mercury 2.5 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.

Keep exploring

More comparisons

Against the newest arrivals

GPT-5.1-Codex-Mini logoDeepSeek V4 Flash Vision Exp logo
GPT-5.1-Codex-Mini vs DeepSeek V4 Flash Vision ExpLanded Sep 2026
Mercury 2.5 logoSolar Pro 4 logo
Mercury 2.5 vs Solar Pro 4Landed Sep 2026
GPT-5.1-Codex-Mini logoHy3 logo
GPT-5.1-Codex-Mini vs Hy3Landed Sep 2026
Mercury 2.5 logoQwen3.7 Flash logo
Mercury 2.5 vs Qwen3.7 FlashLanded Sep 2026
GPT-5.1-Codex-Mini logoLing 3.0 Flash logo
GPT-5.1-Codex-Mini vs Ling 3.0 FlashLanded Sep 2026
Mercury 2.5 logoMuse Glimmer 30B logo
Mercury 2.5 vs Muse Glimmer 30BLanded Sep 2026
GPT-5.1-Codex-Mini logoGLM 5.3 logo
GPT-5.1-Codex-Mini vs GLM 5.3Landed Sep 2026
Mercury 2.5 logoTernary Bonsai 2 27B logo
Mercury 2.5 vs Ternary Bonsai 2 27BLanded Sep 2026

Same lab, same size, long tail

GPT-5.1-Codex-Mini logoGPT-6 Astra Pro logo
GPT-5.1-Codex-Mini vs GPT-6 Astra ProSame lab
GPT-5.1-Codex-Mini logoGPT-6 Astra logo
GPT-5.1-Codex-Mini vs GPT-6 AstraSame lab
Mercury 2.5 logoMercury 2.5 Preview logo
Mercury 2.5 vs Mercury 2.5 PreviewSame lab
Mercury 2.5 logoMercury logo
Mercury 2.5 vs MercurySame lab
Mercury 2.5 logoHorizon Alpha logo
Mercury 2.5 vs Horizon AlphaSame size
Mercury 2.5 logoHorizon Beta logo
Mercury 2.5 vs Horizon BetaSame size
Mercury 2.5 logoHunter Alpha logo
Mercury 2.5 vs Hunter AlphaNew provider
GPT-5.1-Codex-Mini logoHy4 Preview logo
GPT-5.1-Codex-Mini vs Hy4 PreviewSame size

Model pages

GPT-5.1-Codex-Mini logo
GPT-5.1-Codex-Mini59 outputs, specs and price
Mercury 2.5 logo
Mercury 2.520 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
  • Default Index
  • 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