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...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.00000026 | $0.260 |
| completion | 0.00000038 | $0.380 |
| input_cache_read | 0.00000013 | $0.130 |
{
"temperature": 1,
"top_p": 0.95,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
}