Skip to content
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare Models
  • All Models
  • Image Comparison
  • Audio Comparison
  • Image Generation
  • Best AI For...
  • Arena
  • API Pricing
  • Challenges

Discover

  • SubjectiveBench
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Jailbreak
  • Model Updates
  • Provider Status
  • AI Creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
  1. Home
  2. /
  3. Compare
  4. /
  5. Devstral 2 2512vsGPT OSS 120B
Updated Dec 2025

Devstral 2 2512vsGPT OSS 120B

Devstral 2 2512 is the newer model, released after GPT OSS 120B.

Devstral 2 2512 and GPT OSS 120B compared across 35 shared prompts
SpecDevstral 2 2512GPT OSS 120B
Input price—$0.18/M tokens
Output price—$0.8/M tokens
Context window—131K tokens
WeightsOpenOpen
Free API (OpenRouter)NoNo
ReleasedDec 2025Aug 2025
Our Verdict
Devstral 2 2512
Devstral 2 2512
GPT OSS 120B
GPT OSS 120B

Not enough votes to call it. On the specs, nothing separates them.

Too close to call
API pricing

Cost per 1M tokens

Devstral 2 2512
Input
—
Output
—
GPT OSS 120B
Input
$0.18
Output
$0.80
Where to run it

19 hosts, cheapest first

Devstral 2 25121 host
HostInOutContextUptime
Mistral$0.40 in·$2.00 out·262k·100% up
GPT OSS 120B18 hosts
HostInOutContextUptime
AAkashMLbf16$0.03 in·$0.17 out·131k·99.9% upCCoreWeavefp4$0.03 in·$0.17 out·131k·99.9% upDDeepInfrabf16$0.04 in·$0.17 out·131k·99.4% upDDigitalOcean$0.06 in·$0.39 out·128k·99.7% upMMancerfp8$0.06 in·$0.50 out·131k·99.6% upGoogle Vertex AI$0.09 in·$0.36 out·131k·99.9% up
12 more hostsFewer hosts
BBasetenfp4$0.10 in·$0.50 out·128k·100% upPParasailfp4$0.10 in·$0.75 out·131k·100% upSSambaNova$0.14 in·$0.95 out·131k·96.9% upAmazon Bedrock$0.15 in·$0.60 out·131k·98.1% upGroq$0.15 in·$0.60 out·131k·100% upNNebiusfp4$0.15 in·$0.60 out·131k·96.2% upTTogether$0.15 in·$0.60 out·131k·98.8% upCCerebrasfp16$0.35 in·$0.75 out·131k·100% upNNovitafp4degraded$0.05 in·$0.25 out·131k·86.7% upSSiliconFlowfp8degraded$0.05 in·$0.45 out·131k·84.3% upPPhaladegraded$0.15 in·$0.60 out·131k·88.8% upMMaradegraded$0.15 in·$0.75 out·131k·86% up

Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.

Writing DNA

Style Comparison

Similarity
47%

Devstral 2 2512 uses 2.9x more lists

Devstral 2 2512
GPT OSS 120B
56%Vocabulary52%
14wSentence Length19w
0.51Hedging0.28
8.8Bold7.4
5.3Lists1.8
0.31Emoji0.15
1.11Headings0.73
0.18Transitions0.17
Based on 14 + 21 text responses
Research

What we learned reading every model

FAQ

Common questions

Keep exploring

More comparisons

Devstral 2 2512 logoOx Alpha logo
Devstral 2 2512 vs Ox AlphaNew provider
Devstral 2 2512 logoMiniMax M3 logo
Devstral 2 2512 vs MiniMax M3New provider
Devstral 2 2512 logoGPT OSS 20B logo
Devstral 2 2512 vs GPT OSS 20BCross-provider
Devstral 2 2512 logoClaude Opus 4 logo
Devstral 2 2512 vs Claude Opus 4New provider
Devstral 2 2512 logoLlama 4 Maverick logo
Devstral 2 2512 vs Llama 4 MaverickNew provider
Devstral 2 2512 logoLlama 4 Scout logo
Devstral 2 2512 vs Llama 4 ScoutNew provider
Devstral 2 2512 logoMercury logo
Devstral 2 2512 vs MercuryNew provider
Devstral 2 2512 logoMercury 2 logo
Devstral 2 2512 vs Mercury 2New provider
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare Models
  • All Models
  • Image Comparison
  • Audio Comparison
  • Image Generation
  • Best AI For...
  • Arena
  • API Pricing
  • Challenges

Discover

  • SubjectiveBench
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Jailbreak
  • Model Updates
  • Provider Status
  • AI Creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed