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 | 671B |
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 | 128k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.25SiliconFlow |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $1.00SiliconFlow |
| — | $100SiliconFlow · fp8 | |
| Overview | ||
| Company | DeepSeek | DeepSeek |
| Release date | Sep 5 2024 | Mar 24 2025 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
DeepSeek V2.5vsClaude Haiku 5.5DeepSeek V3-0324vsClaude Haiku 5.5DeepSeek V2.5vsGPT-6.1 SolDeepSeek V3-0324vsGPT-6.1 SolDeepSeek V2.5vsGemini 4 ArgonDeepSeek V3-0324vsGemini 4 ArgonDeepSeek V2.5vsMuse Spark OpenDeepSeek V3-0324vsMuse Spark OpenDeepSeek V2.5vsGrok 4.7DeepSeek V3-0324vsGrok 4.7DeepSeek V2.5vsMistral Large 4DeepSeek V3-0324vsMistral Large 4Frequently asked questions
DeepSeek V2.5 and DeepSeek V3-0324 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. DeepSeek V2.5 shipped 200 days before DeepSeek V3-0324, so benchmark comparisons should account for the intervening progress.
DeepSeek V2.5 has 236B parameters, while DeepSeek V3-0324 has 671B. Context windows are 128k (DeepSeek V2.5) vs 128k (DeepSeek V3-0324).
Direct benchmark comparisons are unavailable — DeepSeek V2.5 and DeepSeek V3-0324 don't publish scores on any of the same benchmarks.