DeepSeek V3.1 vs DeepSeek V4.1 Flash 1017
Lower and Larger mark one number at a time; they don’t rank the models. How well a model does depends on your task; see Benchmarks for measured results.
| Detail | DeepSeek V3.1deepseek/deepseek-v3.1 | DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017 |
|---|---|---|
| Maker | deepseek | deepseek |
| Kind | Chat | Chat |
| Input per 1M tokens | $0.2625 | $0.07875 Lower |
| Cached input per 1M tokens | $0.1365 | $0.001575 |
| Cache write per 1M tokens | Same as input | Same as input |
| Output per 1M tokens | $0.9975 | $0.315 Lower |
| Context window | 163,840 tokens | 1,048,576 tokens Larger |
| Max output | 128,000 tokens | 262,144 tokens Larger |
| Capabilities | Reasoning, tool use | Reasoning, tool use, vision |
| Takes | Text | Text, image |
| Returns | Text | Text |
| Zero data retention | Not on every provider | Not on every provider |
| No training on requests | Not on every provider | Not on every provider |
| Released | 2025-08-21 | 2026-10-17 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | DeepSeek V3.1 | DeepSeek V4.1 Flash 1017 |
|---|---|---|
| 1,000 tokens in, 200 out | $0.000462 | $0.000142 |
| 10,000 tokens in, 1,000 out | $0.003623 | $0.001103 |
| 100,000 tokens in, 4,000 out | $0.03024 | $0.009135 |