Compare models
Up to 4 models side by side.
Provider | DeepSeek |
|---|---|
Listed Date added to OpenRouter | Dec 1, 2025 |
Input price USD per 1M tokens | $0.26 |
Output price USD per 1M tokens | $0.38 |
Workload cost Chat reply (2K in, 500 out) | $0.0007 |
Context window | 164K |
Max output | 147K |
Output speed tokens per second | 38 |
Time to first token seconds | 3.25s |
Intelligence Index Artificial Analysis Intelligence Index: a composite of reasoning, knowledge, math and coding evaluations. | n/a |
Engineering Index Artificial Analysis Engineering Index: engineering and technical problem solving. | n/a |
Inputs | text |
Open weights | Yes |
Good at | open-weightslow-cost |
Notes | DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism... |
Best value in each row is highlighted. Share this page's URL to share the comparison.