DeepSeek V4.1 Flash vs Mistral Large 4
DeepSeek V4.1 Flash (DeepSeek) and Mistral Large 4 (Mistral) are listed at different prices. DeepSeek V4.1 Flash costs less: $0.0498 per 1M input tokens and $0.199 per 1M output tokens, against $0.70 and $2.10 for Mistral Large 4. Both hold 1,048,576 tokens of context. DeepSeek V4.1 Flash can write up to 393,216 tokens in one response, against 262,144 for Mistral Large 4. Both accept text and images and produce text.
DeepSeek: DeepSeek V4.1 Flash and Mistral: Mistral Large 4 both accept text and images, produce text, support tools, structured outputs, response formats and reasoning, and have 1,048,576-token context windows. Their maximum output limits are 393,216 and 262,144 tokens, respectively.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | DeepSeek V4.1 Flash | Mistral Large 4 |
|---|---|---|
| Maker | DeepSeek | Mistral |
| Added to catalog | 10 Sep 2026 | 6 Oct 2026 |
| Input, per 1M tokens | $0.0498 | $0.70 |
| Output, per 1M tokens | $0.199 | $2.10 |
| Cached input read, per 1M | $0.001 | $0.07 |
| Context windowTokens | 1,048,576 | 1,048,576 |
| Max outputTokens | 393,216 | 262,144 |
| Accepts | image, 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 V4.1 Flash | Mistral Large 4 |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0001 | $0.0010 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0014 | $0.019 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0019 | $0.025 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0078 | $0.108 |
Which to choose
Choose DeepSeek V4.1 Flash if
- Input tokens cost less: $0.0498 against $0.70 per 1M
- Output tokens cost less: $0.199 against $2.10 per 1M
- Cached input costs less: $0.001 against $0.07 per 1M
- You need longer answers in one response: 393,216 tokens against 262,144
Choose Mistral Large 4 if
No row of the table favours Mistral Large 4. The difference, if there is one, is in the answers it writes: try it on your own task.
Mistral Large 4 detailsNeither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.