DeepSeek Pro Latest vs DeepSeek V4.1 Flash 1017
DeepSeek Pro Latest (DeepSeek) and DeepSeek V4.1 Flash 1017 (DeepSeek) are listed at different prices. DeepSeek Pro Latest costs less for input, $0.0999 per 1M tokens against $0.15; DeepSeek V4.1 Flash 1017 costs less for output, $0.60 per 1M tokens against $8.00. Both hold 1,048,576 tokens of context. DeepSeek Pro Latest accepts text and produces text; DeepSeek V4.1 Flash 1017 accepts text and images and produces text.
DeepSeek: DeepSeek Pro Latest accepts text, while DeepSeek: DeepSeek V4.1 Flash 1017 accepts text and images; both produce text, support tools, structured outputs, response formats, and reasoning, and have the same context and output limits.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | DeepSeek Pro Latest | DeepSeek V4.1 Flash 1017 |
|---|---|---|
| Maker | DeepSeek | DeepSeek |
| Added to catalog | 14 Sep 2026 | 17 Oct 2026 |
| Input, per 1M tokens | $0.0999 | $0.15 |
| Output, per 1M tokens | $8.00 | $0.60 |
| Cached input read, per 1M | $0.0999 | $0.003 |
| Context windowTokens | 1,048,576 | 1,048,576 |
| Max outputTokens | 393,216 | 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 Pro Latest | DeepSeek V4.1 Flash 1017 |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0024 | $0.0003 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0089 | $0.0042 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.019 | $0.0057 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.027 | $0.023 |
Which to choose
Choose DeepSeek Pro Latest if
- Input tokens cost less: $0.0999 against $0.15 per 1M
Choose DeepSeek V4.1 Flash 1017 if
- Output tokens cost less: $0.60 against $8.00 per 1M
- Cached input costs less: $0.003 against $0.0999 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.