DeepSeek V4 Flash vs DeepSeek V4 Flash 0731
Price and specs side by side · USD per 1M tokens · verified 2026-10-11
// side by side
| metric | DeepSeek V4 Flash | DeepSeek V4 Flash 0731 |
|---|
| input / 1M | $0.09 | $0.06 |
| output / 1M | $0.18 | $0.18 |
| blended (3:1) | $0.1125 | $0.09 |
| cache read / 1M | $0.018 | $0.015 |
| context | 1.05M | 1.05M |
| max output | 16.4K | 384K |
| input types | text | text |
| reasoning | yes | yes |
| tool calling | yes | yes |
| structured output | yes | yes |
| open weights | yes | yes |
| released | 2026-04-24 | 2026-07-31 |
| knowledge cutoff | 2025-05 | 2025-05 |
| lab | DeepSeek | DeepSeek |
// monthly cost scenarios
| workload | tokens in / out | DeepSeek V4 Flash | DeepSeek V4 Flash 0731 |
|---|
| Chatbot | 10M / 2M | $1.26 | $0.96 |
| RAG app | 50M / 5M | $5.40 | $3.90 |
| Coding agent | 20M / 10M | $3.60 | $3.00 |
// verdict
- DeepSeek V4 Flash 0731 is 20% cheaper than DeepSeek V4 Flash on a blended 3:1 input/output basis.