DeepSeek-V4-Flash vs DeepSeek-V4-Pro
Direct spec comparison of DeepSeek-V4-Flash (from DeepSeek) and DeepSeek-V4-Pro (from DeepSeek). Want a 3- or 4-way comparison? Open the multi-model tool →
 DeepSeek-V4-FlashDeepSeek | DeepSeek-V4-Pro DeepSeek | |
|---|---|---|
| Vendor | DeepSeek | DeepSeek |
| Family | DeepSeek | DeepSeek |
| Release date | 2026-04-22 | 2026-04-22 |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Parameters | 284B (13B active) | 1.6T (49B active) |
| Modality | text | text |
| License | MIT | MIT |
| Source | open weights | open weights |
| Description | Smaller, faster sibling to DeepSeek-V4-Pro. Same 1M context window with a much lighter 284B / 13B-active MoE. | DeepSeek's flagship open-weight MoE. 1.6T parameters with 49B activated, 1M-token context, and a hybrid attention scheme (CSA + HCA) that delivers long-context inference at ~27% of V3.2's FLOPs. |
| Links |
More like this
Looking for a different head-to-head? Build your own comparison on the multi-model tool.
Or see all DeepSeek-V4-Flash details / DeepSeek-V4-Pro details.