Mistral Devstral MediumvsGPT-4
Mistral Devstral Medium is cheaper than GPT-4 at $0.4/M vs $30/M input tokens.
| Spec | Mistral Devstral Medium | GPT-4 |
|---|---|---|
| Input price | $0.4/M tokens | $30/M tokens |
| Output price | $2/M tokens | $60/M tokens |
| Context window | — | 8K tokens |
| Weights | — | Closed |
| Free API (OpenRouter) | No | No |
| Released | Jul 2025 | May 2023 |
Our Verdict
GPT-4
Mistral Devstral MediumRunner-up
Not enough votes to call it. On the specs, GPT-4 has the edge: bigger model tier, bigger context window, major provider backing.
Mistral Devstral Medium costs 30x less per token.
Too close to call
API pricing
Cost per 1M tokens
Mistral Devstral Medium
Input
$0.40
75× cheaper
Output
$2.00
30× cheaper
GPT-4
Input
$30.00
Output
$60.00
Mistral Devstral Medium is cheaper on both: 75× input, 30× output.
Where to run it
2 hosts
Mistral Devstral Medium
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.
Writing DNA
Style Comparison
Similarity
65%
Mistral Devstral Medium uses 18.8x more headings
Mistral Devstral Medium
GPT-4
50%Vocabulary59%
18wSentence Length18w
0.50Hedging1.10
4.1Bold0.8
4.8Lists2.5
0.00Emoji0.00
0.19Headings0.00
0.29Transitions0.45
Based on 27 + 15 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
More comparisons
Mistral Devstral Medium vs Gemini 2.5 Pro Preview 06-05New provider
Mistral Devstral Medium vs Ox AlphaNew provider
Mistral Devstral Medium vs Claude Opus 4New provider
Mistral Devstral Medium vs Claude Opus 4.1New provider
Mistral Devstral Medium vs Qwen3.5 Plus 2026-04-20New provider
Mistral Devstral Medium vs Qwen3.6 27BNew provider
Mistral Devstral Medium vs Qwen3.6 35B A3BNew provider
Mistral Devstral Medium vs Qwen3.6 FlashNew provider