DeepSeek V3.2vsGPT OSS 120B
GPT OSS 120B is cheaper than DeepSeek V3.2 at $0.18/M vs $0.28/M input tokens.
| Spec | DeepSeek V3.2 | GPT OSS 120B |
|---|---|---|
| Input price | $0.28/M tokens | $0.18/M tokens |
| Output price | $0.42/M tokens | $0.8/M tokens |
| Context window | 131K tokens | 131K tokens |
| Weights | Open | Open |
| Free API (OpenRouter) | No | No |
| Released | Dec 2025 | Aug 2025 |
Our Verdict
DeepSeek V3.2
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
DeepSeek V3.2
Input
$0.28
Output
$0.42
1.9× cheaper
GPT OSS 120B
Input
$0.18
1.6× cheaper
Output
$0.80
GPT OSS 120B wins input (1.6× cheaper)·DeepSeek V3.2 wins output (1.9× cheaper)
Where to run it
33 hosts, cheapest first
DeepSeek V3.215 hosts
GMI Cloudfp8$0.21 in$0.31 out164k99.8% upStreamLakefp8$0.21 in$0.32 out128k99.6% upDigitalOcean$0.25 in$0.80 out164k97.8% upSiliconFlowfp8$0.26 in$0.42 out164k98.1% upAtlasCloudfp8$0.26 in$0.38 out164k99.7% upDeepInfrafp4$0.26 in$0.38 out164k99.5% up
9 more hostsFewer hosts
Novitafp8$0.27 in$0.40 out164k100% upBaidu Qianfanfp8$0.28 in$0.42 out131k100% upVenice$0.33 in$0.48 out160k99.4% upAlibaba Cloudfp8$0.37 in$1.11 out131k99.3% upFriendli$0.50 in$1.50 out164k99.9% upGoogle Vertex AI$0.56 in$1.68 out164k99.2% upPhala$1.00 in$1.00 out164k98.9% upMara$3.00 in$4.50 out33k89.3% upSambaNova$3.00 in$4.50 out33k96.5% up
GPT OSS 120B18 hosts
AkashMLbf16$0.03 in$0.17 out131k99.9% upCoreWeavefp4$0.03 in$0.17 out131k99.9% upDeepInfrabf16$0.04 in$0.17 out131k99.4% upDigitalOcean$0.06 in$0.39 out128k99.7% upMancerfp8$0.06 in$0.50 out131k99.6% upGoogle Vertex AI$0.09 in$0.36 out131k99.9% up
12 more hostsFewer hosts
Basetenfp4$0.10 in$0.50 out128k100% upParasailfp4$0.10 in$0.75 out131k100% upSambaNova$0.14 in$0.95 out131k96.9% upAmazon Bedrock$0.15 in$0.60 out131k98.1% upGroq$0.15 in$0.60 out131k100% upNebiusfp4$0.15 in$0.60 out131k96.2% upTogether$0.15 in$0.60 out131k98.8% upCerebrasfp16$0.35 in$0.75 out131k100% upNovitafp4degraded$0.05 in$0.25 out131k86.7% upSiliconFlowfp8degraded$0.05 in$0.45 out131k84.3% upPhaladegraded$0.15 in$0.60 out131k88.8% upMaradegraded$0.15 in$0.75 out131k86% up
Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.
Writing DNA
Style Comparison
Similarity
52%
GPT OSS 120B uses 15.4x more emoji
DeepSeek V3.2
GPT OSS 120B
54%Vocabulary52%
29wSentence Length19w
0.58Hedging0.28
5.9Bold7.4
4.8Lists1.8
0.00Emoji0.15
0.74Headings0.73
0.12Transitions0.17
Based on 28 + 21 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
More comparisons
DeepSeek V3.2 vs Ox AlphaNew provider
DeepSeek V3.2 vs MiniMax M3New provider
DeepSeek V3.2 vs GPT OSS 20BCross-provider
DeepSeek V3.2 vs MiniMax M2.7New provider
DeepSeek V3.2 vs Mistral Large 3 2512New provider
DeepSeek V3.2 vs Mistral Medium 3New provider
DeepSeek V3.2 vs Mistral Medium 3.1New provider
DeepSeek V3.2 vs Mistral NemoNew provider