DeepSeek V4.1 Flash vs Mistral Small 4: cost per task
DeepSeek V4.1 Flash is cheaper on 13 of 14 tasks and about 4.0x cheaper on average (geometric mean).
| Task | DeepSeek V4.1 Flash | Mistral Small 4 | Difference |
|---|---|---|---|
| Answer a chat question | 0.09¢ | 0.08¢ | 1.1x |
| Reply to a customer email | 0.03¢ | 0.22¢ | 7.1x |
| Write a 1,500-word blog post | 0.04¢ | 0.47¢ | 10.5x |
| Write 10 product descriptions | 0.04¢ | 0.19¢ | 4.6x |
| Translate 1,000 words | 0.18¢ | 0.75¢ | 4.2x |
| Proofread one page (500 words) | 0.04¢ | 0.26¢ | 6.0x |
| Summarize a 20-page PDF | 0.12¢ | 0.33¢ | 2.7x |
| Extract data from an invoice | 0.04¢ | 0.16¢ | 3.7x |
| Analyze a 200-row spreadsheet | 0.26¢ | 0.71¢ | 2.7x |
| Answer from 5 retrieved documents (RAG) | 0.08¢ | 0.25¢ | 3.1x |
| Classify 100 support tickets | 0.08¢ | 0.46¢ | 5.8x |
| Review 500 lines of code | 0.26¢ | 0.62¢ | 2.3x |
| Write a SQL query | 0.03¢ | 0.19¢ | 6.0x |
| Run a 50-step coding agent | 2.4¢ | 13¢ | 5.6x |
Specs and list prices
| DeepSeek V4.1 Flash | Mistral Small 4 | |
|---|---|---|
| Input per 1M | $0.072 | $0.15 |
| Output per 1M | $0.14 | $0.60 |
| Cached input per 1M | $0.002 | $0.015 |
| Context | 1M | 262K |
| Providers | 34 | 4 |
| Reasoning | default | default |
| LMArena Text | 1475 | - |
| Released | Sep 10, 2026 | Mar 16, 2026 |
FAQ
Is DeepSeek V4.1 Flash or Mistral Small 4 cheaper?
DeepSeek V4.1 Flash is cheaper on 13 of 14 tasks and about 4.0x cheaper on average (geometric mean).
How much does DeepSeek V4.1 Flash cost compared to Mistral Small 4 per token?
DeepSeek V4.1 Flash: $0.072 input and $0.14 output per 1M tokens. Mistral Small 4: $0.15 input and $0.60 output. Token prices alone mislead - models use different numbers of tokens for the same task, which is what the task table shows.