GPT OSS 120BvsKimi K2.6
GPT OSS 120B is cheaper than Kimi K2.6 at $0.18/M vs $0.95/M input tokens.
| Spec | GPT OSS 120B | Kimi K2.6 |
|---|---|---|
| Input price | $0.18/M tokens | $0.95/M tokens |
| Output price | $0.8/M tokens | $4/M tokens |
| Context window | 131K tokens | 262K tokens |
| Weights | Open | Open |
| Free API (OpenRouter) | No | No |
| Released | Aug 2025 | Apr 2026 |
Our Verdict
GPT OSS 120B
Kimi K2.6
Not enough votes to call it. On the specs, nothing separates them.
GPT OSS 120B costs 5.0x less per token.
Too close to call
Reviewing agent-written code?See a Brief PR report
API pricing
Cost per 1M tokens
GPT OSS 120B
Input
$0.18
5.3× cheaper
Output
$0.80
5.0× cheaper
Kimi K2.6
Input
$0.95
Output
$4.00
GPT OSS 120B is cheaper on both: 5.3× input, 5.0× output.
Where to run it
39 hosts, cheapest first
GPT OSS 120B19 hosts
AkashMLbf16$0.03 in$0.17 out131k99.9% upCoreWeavefp4$0.03 in$0.17 out131k99.9% upDekaLLMbf16$0.03 in$0.18 out131k99.2% upDeepInfrabf16$0.04 in$0.17 out131k98.8% upDigitalOcean$0.06 in$0.39 out128k99.8% upMancerfp8$0.06 in$0.50 out131k99.3% up
13 more hostsFewer hosts
Google Vertex AI$0.09 in$0.36 out131k99.9% upBasetenfp4$0.10 in$0.50 out128k100% upParasailfp4$0.10 in$0.75 out131k97.5% upSambaNova$0.14 in$0.95 out131k97.7% upAmazon Bedrock$0.15 in$0.60 out131k100% upGroq$0.15 in$0.60 out131k100% upNebiusfp4$0.15 in$0.60 out131k98.7% upSiliconFlowfp8$0.15 in$0.60 out131k95.8% upCerebrasfp16$0.35 in$0.75 out131k100% upNovitafp4degraded$0.05 in$0.25 out131k96.2% upPhaladegraded$0.15 in$0.60 out131k96.6% upTogetherdegraded$0.15 in$0.60 out131k94.9% upMaradegraded$0.15 in$0.75 out131k58.1% up
Kimi K2.620 hosts
Baidu Qianfanfp4$0.58 in$2.44 out262k99.7% upChutesint4$0.58 in$3.40 out262k98.2% upDecartfp4$0.59 in$2.47 out262k99.6% upInceptronint4$0.59 in$2.45 out262k99.5% upStreamLakefp8$0.60 in$2.52 out256k96.5% upCoreWeavefp4$0.65 in$3.41 out262k99.8% up
14 more hostsFewer hosts
DeepInfrafp4$0.75 in$3.50 out262k98.7% upParasailint4$0.75 in$3.50 out262k99.6% upVeniceint4$0.75 in$3.50 out256k97.5% upSiliconFlowfp8$0.77 in$3.40 out262k99.7% upNovita$0.80 in$3.40 out262k99.3% upAtlasCloudint4$0.95 in$4.00 out262k98.4% upBasetenfp4$0.95 in$4.00 out262k47.2% upCloudflare Workers AI$0.95 in$4.00 out262k99.9% upDigitalOcean$0.95 in$4.00 out262k99.6% upFireworks$0.95 in$4.00 out262k0.6% upMoonshot AIint4$0.95 in$4.00 out262k99.8% upCrusoebf16degraded$0.70 in$3.50 out262k99.4% upGMI Cloudfp8degraded$0.85 in$3.60 out262k96.5% upPhaladegraded$1.09 in$4.60 out262k97.9% up
Per million tokens. Prices and uptime via OpenRouter, checked 11 Sep 2026.
Writing DNA
Style Comparison
Similarity
61%
GPT OSS 120B uses 4.5x more emoji
GPT OSS 120B
Kimi K2.6
52%Vocabulary57%
19wSentence Length16w
0.28Hedging0.37
7.4Bold4.3
1.8Lists2.0
0.15Emoji0.03
0.73Headings0.53
0.17Transitions0.16
Based on 21 + 27 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
More comparisons
GPT OSS 120B vs Ox AlphaNew provider
GPT OSS 120B vs MiniMax M3New provider
GPT OSS 120B vs Claude Opus 4New provider
GPT OSS 120B vs Claude Opus 4.1New provider
GPT OSS 120B vs Llama 4 ScoutNew provider
GPT OSS 120B vs MercuryNew provider
Kimi K2.6 vs Mercury 2New provider
GPT OSS 120B vs Mercury 2.5 PreviewNew provider