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. Claude Sonnet 4.5vsOpenAI Codex Mini
Updated Sep 2025

Claude Sonnet 4.5vsOpenAI Codex Mini

OpenAI Codex Mini is cheaper than Claude Sonnet 4.5 at $1.5/M vs $3/M input tokens.

Claude Sonnet 4.5 and OpenAI Codex Mini compared across 10 shared prompts
SpecClaude Sonnet 4.5OpenAI Codex Mini
Input price$3/M tokens$1.5/M tokens
Output price$15/M tokens$6/M tokens
Context window200K tokens200K tokens
WeightsClosed—
Free API (OpenRouter)NoNo
ReleasedSep 2025May 2025
SWE-bench Verified77.2%71.3%
Side by side

Same prompt, both answers

Opening lines from 2 of the 10 prompts both answered. Formatting stripped, words untouched.

Generate a Stand-Up Routine

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

Claude Sonnet 4.5735 words
"ADULTING IS A SCAM" [Walking on stage] So I turned 35 last month, and I've realized something important: adulting is a scam. It's a pyramid scheme, and our parents are the ones who recruited us. You know what nobody tells you about being an adult? How much TIME you spend just... waiting for repair people.
Read the full answer
OpenAI Codex Mini595 words
[Comedian walks onstage] Hey, everyone! Great to see you all tonight. I'm Jamie—if you thought that intro was enthusiastic, you should've seen me when I realized this place has Wi-Fi. Seriously, though, I love stand-up.
Read the full answer

Stochastic Consistency Test

Generate 5 jokes. How many are unique?

Claude Sonnet 4.583 words
5 Jokes Why don't scientists trust atoms? Because they make up everything! I told my wife she was drawing her eyebrows too high. She looked surprised. Why did the scarecrow win an award? He was outstanding in his field. I'm reading a book about anti-gravity. It's impossible to put down. Why don't eggs tell jokes?
Read the full answer
OpenAI Codex Mini75 words
Sure—here are five jokes: I asked the librarian if books about paranoia were available. She whispered, "They're right behind you." Why did the tomato turn red? Because it saw the salad dressing. I bought a boat because it was for sail. Don't trust stairs—they're always up to something.
Read the full answer
Our Verdict
Claude Sonnet 4.5
Claude Sonnet 4.5
OpenAI Codex Mini
OpenAI Codex MiniRunner-up

Not enough votes to call it. On the specs, Claude Sonnet 4.5 has the edge: bigger model tier, newer.

Too close to call

Reviewing agent-written code?See a Brief PR report

API pricing

Cost per 1M tokens

Claude Sonnet 4.5
Input
$3.00
Output
$15.00
OpenAI Codex Mini
Input
$1.50
2.0× cheaper
Output
$6.00
2.5× cheaper

OpenAI Codex Mini is cheaper on both: 2.0× input, 2.5× output.

Where to run it

4 hosts

Claude Sonnet 4.54 hosts
HostInOutContextUptime
Amazon Bedrock$3.00 in·$15.00 out·1M·100% upAzure AI Foundry$3.00 in·$15.00 out·200k·99.5% upAnthropic$3.00 in·$15.00 out·1M·100% upGoogle Vertex AI$3.00 in·$15.00 out·1M·100% up
OpenAI Codex Mini

No hosts listed on OpenRouter.

Per million tokens. Prices and uptime via OpenRouter, checked 20 Sep 2026.

Research

What we learned reading every model

FAQ

Common questions

Claude Sonnet 4.5 is developed by Anthropic while OpenAI Codex Mini is developed by OpenAI. Claude Sonnet 4.5 has a 200K token context window vs OpenAI Codex Mini's 200K. You can compare their actual outputs across 10 challenges on Rival to see how they differ in practice.

It depends on your use case. Claude Sonnet 4.5 and OpenAI Codex Mini each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 10 challenges so you can judge which fits your needs best.

Claude Sonnet 4.5 costs $3/M input tokens and OpenAI Codex Mini costs $1.5/M input tokens. OpenAI Codex Mini 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 Claude Sonnet 4.5 and OpenAI Codex Mini 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

Claude Sonnet 4.5 logoGPT-6 Astra Pro logo
Claude Sonnet 4.5 vs GPT-6 Astra ProLanded Sep 2026
OpenAI Codex Mini logoGPT-6 Astra logo
OpenAI Codex Mini vs GPT-6 AstraLanded Sep 2026
Claude Sonnet 4.5 logoClaude Fable 5.1 logo
Claude Sonnet 4.5 vs Claude Fable 5.1Landed Sep 2026
OpenAI Codex Mini logoMuse Spark 1.3 logo
OpenAI Codex Mini vs Muse Spark 1.3Landed Sep 2026
Claude Sonnet 4.5 logoHy4 Preview logo
Claude Sonnet 4.5 vs Hy4 PreviewLanded Sep 2026
OpenAI Codex Mini logoGemini 3.8 Flash logo
OpenAI Codex Mini vs Gemini 3.8 FlashLanded Sep 2026
Claude Sonnet 4.5 logoMuse Spark 1.3 Contributor logo
Claude Sonnet 4.5 vs Muse Spark 1.3 ContributorLanded Sep 2026
OpenAI Codex Mini logoMercury 2.5 Preview logo
OpenAI Codex Mini vs Mercury 2.5 PreviewLanded Sep 2026

Same lab, same size, long tail

Claude Sonnet 4.5 logoClaude Opus 4.6 logo
Claude Sonnet 4.5 vs Claude Opus 4.6Same lab
Claude Sonnet 4.5 logoClaude Opus 5 logo
Claude Sonnet 4.5 vs Claude Opus 5Same lab
OpenAI Codex Mini logoGPT-6 Astra Pro logo
OpenAI Codex Mini vs GPT-6 Astra ProSame lab
OpenAI Codex Mini logoGPT-5.6 Luna logo
OpenAI Codex Mini vs GPT-5.6 LunaSame lab
OpenAI Codex Mini logoGrok 4.20 Beta logo
OpenAI Codex Mini vs Grok 4.20 BetaNew provider
OpenAI Codex Mini logoGrok 4.20 Multi-Agent Beta logo
OpenAI Codex Mini vs Grok 4.20 Multi-Agent BetaNew provider
OpenAI Codex Mini logoGrok 4.3 logo
OpenAI Codex Mini vs Grok 4.3New provider
OpenAI Codex Mini logoGrok 4.5 logo
OpenAI Codex Mini vs Grok 4.5New provider

Model pages

Claude Sonnet 4.5 logo
Claude Sonnet 4.543 outputs, specs and price
OpenAI Codex Mini logo
OpenAI Codex Mini10 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