DeepSeek V4.1 Flash vs DeepSeek V4 Flash (1-flash-1017)
Price and specs side by side · USD per 1M tokens · verified 2026-10-23
// side by side
| metric | DeepSeek V4.1 Flash | DeepSeek V4 Flash (1-flash-1017) |
|---|
| input / 1M | $0.20 | $0.15 |
| output / 1M | $0.60 | $0.60 |
| blended (3:1) | $0.30 | $0.2625 |
| cache read / 1M | $0.006 | $0.003 |
| context | 1.05M | 1.05M |
| max output | 384K | 393.2K |
| input types | text · image | text · image |
| reasoning | yes | yes |
| tool calling | yes | yes |
| structured output | yes | yes |
| open weights | yes | yes |
| released | 2026-09-10 | 2026-10-17 |
| knowledge cutoff | 2025-05 | 2025-05 |
| lab | DeepSeek | DeepSeek |
// monthly cost scenarios
| workload | tokens in / out | DeepSeek V4.1 Flash | DeepSeek V4 Flash (1-flash-1017) |
|---|
| Chatbot | 10M / 2M | $3.20 | $2.70 |
| RAG app | 50M / 5M | $13.00 | $10.50 |
| Coding agent | 20M / 10M | $10.00 | $9.00 |
// verdict
- DeepSeek V4 Flash (1-flash-1017) is 12.5% cheaper than DeepSeek V4.1 Flash on a blended 3:1 input/output basis.
- Chatbot (10M input / 2M output tokens per month): DeepSeek V4 Flash (1-flash-1017) costs $2.70 vs $3.20 for DeepSeek V4.1 Flash, saving $0.50 per month.
- RAG app (50M input / 5M output tokens per month): DeepSeek V4 Flash (1-flash-1017) costs $10.50 vs $13.00 for DeepSeek V4.1 Flash, saving $2.50 per month.
- Coding agent (20M input / 10M output tokens per month): DeepSeek V4 Flash (1-flash-1017) costs $9.00 vs $10.00 for DeepSeek V4.1 Flash, saving $1.00 per month.
// DeepSeek V4.1 Flash or DeepSeek V4 Flash (1-flash-1017): which one to choose
- Choose DeepSeek V4 Flash (1-flash-1017) for cost-sensitive, high-volume workloads.