Mistral Devstral MediumvsGPT OSS 20B
GPT OSS 20B is cheaper than Mistral Devstral Medium at $0.02/M vs $0.4/M input tokens.
| Spec | Mistral Devstral Medium | GPT OSS 20B |
|---|---|---|
| Input price | $0.4/M tokens | $0.02/M tokens |
| Output price | $2/M tokens | $0.1/M tokens |
| Context window | — | 131K tokens |
| Weights | — | Open |
| Free API (OpenRouter) | No | No |
| Released | Jul 2025 | Aug 2025 |
Our Verdict
GPT OSS 20B
Mistral Devstral MediumRunner-up
Not enough votes to call it. On the specs, GPT OSS 20B has the edge: bigger model tier, bigger context window, major provider backing.
GPT OSS 20B costs 20x less per token.
Too close to call
API pricing
Cost per 1M tokens
Mistral Devstral Medium
Input
$0.40
Output
$2.00
GPT OSS 20B
Input
$0.02
20× cheaper
Output
$0.10
20× cheaper
GPT OSS 20B is cheaper on both: 20× input, 20× output.
Where to run it
12 hosts, cheapest first
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
63%
GPT OSS 20B uses 10.2x more emoji
Mistral Devstral Medium
GPT OSS 20B
50%Vocabulary54%
18wSentence Length17w
0.50Hedging0.26
4.1Bold5.9
4.8Lists3.3
0.00Emoji0.10
0.19Headings0.75
0.29Transitions0.32
Based on 27 + 21 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
More comparisons
Mistral Devstral Medium vs Ox AlphaNew provider
Mistral Devstral Medium vs MiniMax M3New provider
Mistral Devstral Medium vs MiniMax M2.7New provider
Mistral Devstral Medium vs Pony AlphaNew provider
Mistral Devstral Medium vs GPT-6 Astra ProCross-provider
Mistral Devstral Medium vs GPT OSS 120BCross-provider
Mistral Devstral Medium vs Granite 4.2 8BNew provider
Mistral Devstral Medium vs Grok 3New provider