DeepSeek V4 Flash 0731 vs DeepSeek V4.1 Flash
DeepSeek V4 Flash 0731 (DeepSeek) and DeepSeek V4.1 Flash (DeepSeek) are listed at different prices. DeepSeek V4 Flash 0731 costs less for input, $0.0443 per 1M tokens against $0.0498; DeepSeek V4.1 Flash costs less for output, $0.199 per 1M tokens against $0.30. Both hold 1,048,576 tokens of context. DeepSeek V4 Flash 0731 can write up to 943,718 tokens in one response, against 393,216 for DeepSeek V4.1 Flash. DeepSeek V4 Flash 0731 accepts text and produces text; DeepSeek V4.1 Flash accepts text and images and produces text.
DeepSeek: DeepSeek V4 Flash 0731 accepts and produces text, while DeepSeek: DeepSeek V4.1 Flash accepts text and images and produces text. Both list a 1,048,576-token context and support tools, structured outputs, response formats, and reasoning; their maximum output limits differ.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | DeepSeek V4 Flash 0731 | DeepSeek V4.1 Flash |
|---|---|---|
| Maker | DeepSeek | DeepSeek |
| Added to catalog | 31 Jul 2026 | 10 Sep 2026 |
| Input, per 1M tokens | $0.0443 | $0.0498 |
| Output, per 1M tokens | $0.30 | $0.199 |
| Cached input read, per 1M | $0.035 | $0.001 |
| Context windowTokens | 1,048,576 | 1,048,576 |
| Max outputTokens | 943,718 | 393,216 |
| Accepts | text | image, text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | Yes | Yes |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | DeepSeek V4 Flash 0731 | DeepSeek V4.1 Flash |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0001 | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0013 | $0.0014 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0019 | $0.0019 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0071 | $0.0078 |
Which to choose
Choose DeepSeek V4 Flash 0731 if
- Input tokens cost less: $0.0443 against $0.0498 per 1M
- You need longer answers in one response: 943,718 tokens against 393,216
Choose DeepSeek V4.1 Flash if
- Output tokens cost less: $0.199 against $0.30 per 1M
- Cached input costs less: $0.001 against $0.035 per 1M
- It has to read images, which the other model does not
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.