Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 236B | 2.8T |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 128k | 1M |
| Overview | ||
| Company | DeepSeek | Moonshot AI |
| Release date | May 6 2024 | Oct 23 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek V2vsClaude Haiku 5.5Kimi K3.1 Pro HighspeedvsClaude Haiku 5.5DeepSeek V2vsGPT-6.1 SolKimi K3.1 Pro HighspeedvsGPT-6.1 SolDeepSeek V2vsGemini 4 ArgonKimi K3.1 Pro HighspeedvsGemini 4 ArgonDeepSeek V2vsMuse Spark OpenKimi K3.1 Pro HighspeedvsMuse Spark OpenDeepSeek V2vsGrok 4.7Kimi K3.1 Pro HighspeedvsGrok 4.7DeepSeek V2vsMistral Large 4Kimi K3.1 Pro HighspeedvsMistral Large 4Frequently asked questions
DeepSeek V2 and Kimi K3.1 Pro Highspeed don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V2 shipped 900 days before Kimi K3.1 Pro Highspeed, so benchmark comparisons should account for the intervening progress.
DeepSeek V2 has 236B parameters, while Kimi K3.1 Pro Highspeed has 2.8T. Context windows are 128k (DeepSeek V2) vs 1M (Kimi K3.1 Pro Highspeed). DeepSeek V2 is open weight, while Kimi K3.1 Pro Highspeed is closed.
Direct benchmark comparisons are unavailable — DeepSeek V2 and Kimi K3.1 Pro Highspeed don't publish scores on any of the same benchmarks.