SF·SIX / MODEL PROFILE
DeepSeek V3.2 Exp
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...
DeepSeek V3.2 Exp costs $0.27 per 1M input tokens and $0.41 per 1M output tokens at the standard tier, the lowest default-region price among the 1 provider SF·SIX tracks, from SiliconFlow (fp8). Updated ; prices checked .
- Developer
- DeepSeek
- Input modalities
- text
- Output modalities
- text
- Context tokens
- 163,840
- Latest price observation
- 2026-10-17
- Lowest paired standard token quote
- $0.27 input / $0.41 output per 1M tokens
Dated price and provider records
| Provider and channel | Input | Output or native rate | Unit and status | Source and observation |
|---|---|---|---|---|
| SiliconFlowOpenRouter | $0.27 | $0.41 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.