Devstral 2 2512vsGPT OSS 20B
Devstral 2 2512 is the newer model, released after GPT OSS 20B.
| Spec | Devstral 2 2512 | GPT OSS 20B |
|---|---|---|
| Input price | — | $0.02/M tokens |
| Output price | — | $0.1/M tokens |
| Context window | — | 131K tokens |
| Weights | Open | Open |
| Free API (OpenRouter) | No | No |
| Released | Dec 2025 | Aug 2025 |
Our Verdict
Devstral 2 2512
GPT OSS 20BRunner-up
Not enough votes to call it. On the specs, Devstral 2 2512 has the edge: bigger model tier, newer.
Too close to call
API pricing
Cost per 1M tokens
Devstral 2 2512
Input
—
Output
—
GPT OSS 20B
Input
$0.02
Output
$0.10
Where to run it
13 hosts, cheapest first
Devstral 2 25121 host
Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.
Writing DNA
Style Comparison
Similarity
48%
Devstral 2 2512 uses 3.0x more emoji
Devstral 2 2512
GPT OSS 20B
56%Vocabulary54%
14wSentence Length17w
0.51Hedging0.26
8.8Bold5.9
5.3Lists3.3
0.31Emoji0.10
1.11Headings0.75
0.18Transitions0.32
Based on 14 + 21 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
More comparisons
Devstral 2 2512 vs Ox AlphaNew provider
Devstral 2 2512 vs MiniMax M3New provider
Devstral 2 2512 vs MiniMax M2.7New provider
Devstral 2 2512 vs GPT OSS 120BCross-provider
Devstral 2 2512 vs GPT-4Cross-provider
Devstral 2 2512 vs GPT-4.1Cross-provider
Devstral 2 2512 vs GPT-4.1 MiniCross-provider
Devstral 2 2512 vs GPT-4.1 NanoCross-provider