Mistral Devstral MediumvsQwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507 is cheaper than Mistral Devstral Medium at $0.11/M vs $0.4/M input tokens.
| Spec | Mistral Devstral Medium | Qwen3 235B A22B Thinking 2507 |
|---|---|---|
| Input price | $0.4/M tokens | $0.11/M tokens |
| Output price | $2/M tokens | $0.6/M tokens |
| Context window | — | 131K tokens |
| Released | Jul 2025 | Jul 2025 |
Our Verdict
Qwen3 235B A22B Thinking 2507
Mistral Devstral MediumRunner-up
Not enough votes to call it. On the specs, Qwen3 235B A22B Thinking 2507 has the edge: bigger model tier, bigger context window.
Qwen3 235B A22B Thinking 2507 costs 3.3x less per token.
Too close to call
API pricing
Cost per 1M tokens
Mistral Devstral Medium
Input
$0.40
Output
$2.00
Qwen3 235B A22B Thinking 2507
Input
$0.11
3.6× cheaper
Output
$0.60
3.3× cheaper
Qwen3 235B A22B Thinking 2507 is cheaper on both — 3.6× input, 3.3× output
Writing DNA
Style Comparison
Similarity
40%
Qwen3 235B A22B Thinking 2507 uses 53.9x more emoji
Mistral Devstral Medium
Qwen3 235B A22B Thinking 2507
50%Vocabulary56%
17wSentence Length14w
0.56Hedging0.37
4.5Bold5.7
5.3Lists4.0
0.00Emoji0.54
0.19Headings0.70
0.32Transitions0.14
Based on 21 + 22 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 GPT OSS 120BNew provider
Mistral Devstral Medium vs Claude Opus 4New provider
Qwen3 235B A22B Thinking 2507 vs Mistral Medium 3.1Cross-provider
Qwen3 235B A22B Thinking 2507 vs Mistral NemoCross-provider
Qwen3 235B A22B Thinking 2507 vs Mistral Small 4Cross-provider
Qwen3 235B A22B Thinking 2507 vs Mistral Small CreativeCross-provider