Compare Cogito V2 Preview Llama 405B from deepcogito and DeepSeek V3.2 from DeepSeek on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.


| Attribute | Cogito V2 Preview Llama 405B | DeepSeek V3.2 |
|---|---|---|
| Input price | Pricing varies by provider | $0.2088/M tokens |
| Output price | Pricing varies by provider | $0.3096/M tokens |
| Context window | 131,072 tokens | 163,840 tokens |
| Intelligence Index | Not available | Not available |
| Coding Index | Not available | 44.2 |
| Agentic Index | Not available | Not available |
| Latency (p50) | Not available | 1.24 s |
| Throughput (p50) | Not available | 53.0 tok/s |
| Provided by | deepcogito | DeepSeek |
| Model page | Cogito V2 Preview Llama 405B model details, providers and pricing | DeepSeek V3.2 model details, providers and pricing |
Benchmark data updated
DeepSeek V3.2 has the longer context window at 163,840 tokens, compared with 131,072 tokens for Cogito V2 Preview Llama 405B.