DeepSeek V4 Flash Vision Exp is cheaper than OpenAI Codex Mini at $0.22/M vs $1.5/M input tokens.
Pokémon battle screen you can actually click. One HTML file.
Which answer wins?
Three minutes of stand-up. Puns are banned.
OpenAI Codex Mini: [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.
DeepSeek V4 Flash Vision Exp: Here’s a 3-minute stand-up routine. No puns. Just observations and slow, painful self-awareness. Thank you! So I’m at that age where I’ve started doing things my parents used to do. Not the good things. I don’t have a garden. I have a cactus that I forgot to water for three months. It died.
Five jokes on demand, then count how many were actually different.
OpenAI Codex Mini: 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.
DeepSeek V4 Flash Vision Exp: Here are 5 jokes: Why don’t scientists trust atoms? Because they make up everything. I told my wife she should embrace her mistakes. She gave me a hug. What do you call a fake noodle? An impasta. Why did the scarecrow win an award? Because he was outstanding in his field. I’m reading a book on anti-gravity.
Not enough votes to call it. On the specs, DeepSeek V4 Flash Vision Exp has the edge: bigger model tier, newer, bigger context window. DeepSeek V4 Flash Vision Exp costs 9.1x less per token.
| Spec | ||
|---|---|---|
| Input price | $1.5/M tokens | $0.22/M tokens |
| Output price | $6/M tokens | $0.66/M tokens |
| Context window | 200K tokens | 1.0M tokens |
| Weights | — | Open |
| Free API (OpenRouter) | No | No |
| Released | May 2025 | Aug 2026 |
| At 10M a month | $15.00 | $2.20 |
Input tokens at list price. No caching, no batch discount.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 29 Sep 2026.
OpenAI Codex Mini is developed by OpenAI while DeepSeek V4 Flash Vision Exp is developed by DeepSeek. OpenAI Codex Mini has a 200K token context window vs DeepSeek V4 Flash Vision Exp's 1.0M. You can compare their actual outputs across 9 challenges on Rival to see how they differ in practice.
It depends on your use case. OpenAI Codex Mini and DeepSeek V4 Flash Vision Exp each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 9 challenges so you can judge which fits your needs best.
OpenAI Codex Mini costs $1.5/M input tokens and DeepSeek V4 Flash Vision Exp costs $0.22/M input tokens. DeepSeek V4 Flash Vision Exp is $1.28/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 OpenAI Codex Mini and DeepSeek V4 Flash Vision Exp 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.