Mistral Devstral MediumvsGPT-5.1-Codex
Mistral Devstral Medium is cheaper than GPT-5.1-Codex at $0.4/M vs $1.25/M input tokens.
| Spec | Mistral Devstral Medium | GPT-5.1-Codex |
|---|---|---|
| Input price | $0.4/M tokens | $1.25/M tokens |
| Output price | $2/M tokens | $10/M tokens |
| Context window | — | 400K tokens |
| Released | Jul 2025 | Nov 2025 |
| SWE-bench Verified | 61.6% | 73.7% |
Our Verdict
GPT-5.1-Codex
Mistral Devstral MediumRunner-up
Not enough votes to call it. On the specs, GPT-5.1-Codex has the edge: bigger model tier, newer, bigger context window, major provider backing.
Mistral Devstral Medium costs 5.0x less per token.
Slight edge
API pricing
Cost per 1M tokens
Mistral Devstral Medium
Input
$0.40
3.1× cheaper
Output
$2.00
5.0× cheaper
GPT-5.1-Codex
Input
$1.25
Output
$10.00
Mistral Devstral Medium is cheaper on both — 3.1× input, 5.0× output
Writing DNA
Style Comparison
Similarity
57%
GPT-5.1-Codex uses 2.6x more headings
Mistral Devstral Medium
GPT-5.1-Codex
50%Vocabulary70%
17wSentence Length17w
0.56Hedging0.39
4.5Bold3.4
5.3Lists3.5
0.00Emoji0.00
0.19Headings0.50
0.32Transitions0.38
Based on 21 + 14 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
More comparisons
Mistral Devstral Medium vs MiniMax M3New 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 Seed 2.0 CodeNew provider
Mistral Devstral Medium vs Seed 2.0 LiteNew provider
Mistral Devstral Medium vs Seed 2.1 TurboNew provider
Mistral Devstral Medium vs Sherlock Dash AlphaNew provider