DeepSeek: DeepSeek V3.2 Expdeepseek
DeepSeek: DeepSeek V3.2 Exp: $0.27/1M input, $0.41/1M output, 164K context. DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
API Pricing (per 1M tokens)
| Input | $0.27 |
| Output | $0.41 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.30 |
Specs & Performance
| Context Length | 164K |
| Max Output | 147K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text → text |
More from deepseek
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the DeepSeek: DeepSeek V3.2 Exp API cost?
DeepSeek: DeepSeek V3.2 Exp costs $0.27/1M input tokens and $0.41/1M output tokens. Blended cost at a 3:1 ratio is about $0.30/1M tokens.
What is the context window of DeepSeek: DeepSeek V3.2 Exp?
DeepSeek: DeepSeek V3.2 Exp supports a 164K token context window with up to 147K output tokens.
Is DeepSeek: DeepSeek V3.2 Exp worth it?
DeepSeek: DeepSeek V3.2 Exp has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.