DeepSeek V3.1vsMistral Devstral Small 1.1
Mistral Devstral Small 1.1 is cheaper than DeepSeek V3.1 at $0.1/M vs $0.2/M input tokens.
| Spec | DeepSeek V3.1 | Mistral Devstral Small 1.1 |
|---|---|---|
| Input price | $0.2/M tokens | $0.1/M tokens |
| Output price | $0.8/M tokens | $0.3/M tokens |
| Context window | 164K tokens | — |
| Released | Aug 2025 | Jul 2025 |
| SWE-bench Verified | 66.0% | 46.8% |
Our Verdict
DeepSeek V3.1
Mistral Devstral Small 1.1Runner-up
Not enough votes to call it. On the specs, DeepSeek V3.1 has the edge: bigger model tier, newer, bigger context window, major provider backing.
Slight edge
API pricing
Cost per 1M tokens
DeepSeek V3.1
Input
$0.20
Output
$0.80
Mistral Devstral Small 1.1
Input
$0.10
2.0× cheaper
Output
$0.30
2.7× cheaper
Mistral Devstral Small 1.1 is cheaper on both — 2.0× input, 2.7× output
Writing DNA
Style Comparison
Similarity
85%
DeepSeek V3.1 uses 2.4x more emoji
DeepSeek V3.1
Mistral Devstral Small 1.1
53%Vocabulary50%
14wSentence Length17w
0.42Hedging0.56
4.0Bold4.3
3.6Lists5.7
0.02Emoji0.00
0.40Headings0.05
0.22Transitions0.34
Based on 23 + 21 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
More comparisons
Mistral Devstral Small 1.1 vs Ox AlphaNew provider
Mistral Devstral Small 1.1 vs MiniMax M3New provider
Mistral Devstral Small 1.1 vs GPT-5New provider
Mistral Devstral Small 1.1 vs Claude Opus 4New provider
Mistral Devstral Small 1.1 vs Qwen3.5 35B A3BNew provider
Mistral Devstral Small 1.1 vs Qwen3.5 397B A17BNew provider
Mistral Devstral Small 1.1 vs Qwen3.5 9BNew provider
Mistral Devstral Small 1.1 vs Qwen3.5 FlashNew provider