DeepSeek Flash Latest vs DeepSeek V4 Flash Latest
DeepSeek Flash Latest (DeepSeek) and DeepSeek V4 Flash Latest (DeepSeek) are listed at different prices. DeepSeek Flash Latest costs less for input, $0.036 per 1M tokens against $0.044; DeepSeek V4 Flash Latest costs less for output, $0.132 per 1M tokens against $0.50. Both hold 1,048,576 tokens of context. DeepSeek Flash Latest can write up to 943,718 tokens in one response, against 131,072 for DeepSeek V4 Flash Latest. DeepSeek Flash Latest accepts text and images and produces text; DeepSeek V4 Flash Latest accepts text and produces text.
DeepSeek: DeepSeek Flash Latest accepts text and images, while DeepSeek: DeepSeek V4 Flash Latest accepts text only. Both produce text, support tools, structured outputs, response formats and reasoning, and have a 1,048,576-token context; their maximum output limits differ.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | DeepSeek Flash Latest | DeepSeek V4 Flash Latest |
|---|---|---|
| Maker | DeepSeek | DeepSeek |
| Added to catalog | 14 Sep 2026 | 1 Aug 2026 |
| Input, per 1M tokens | $0.036 | $0.044 |
| Output, per 1M tokens | $0.50 | $0.132 |
| Cached input read, per 1M | $0.01 | $0.0014 |
| Context windowTokens | 1,048,576 | 1,048,576 |
| Max outputTokens | 943,718 | 131,072 |
| Accepts | image, text | 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 Flash Latest | DeepSeek V4 Flash Latest |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0002 | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0013 | $0.0012 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0021 | $0.0016 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0062 | $0.0068 |
Which to choose
Choose DeepSeek Flash Latest if
- Input tokens cost less: $0.036 against $0.044 per 1M
- You need longer answers in one response: 943,718 tokens against 131,072
- It has to read images, which the other model does not
Choose DeepSeek V4 Flash Latest if
- Output tokens cost less: $0.132 against $0.50 per 1M
- Cached input costs less: $0.0014 against $0.01 per 1M
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.