Gemini 3.8 Flash vs Mistral Small 4: cost per task
Mistral Small 4 is cheaper on 14 of 14 tasks and about 3.7x cheaper on average (geometric mean).
| Task | Gemini 3.8 Flash | Mistral Small 4 | Difference |
|---|---|---|---|
| Answer a chat question | 0.68¢ | 0.08¢ | 8.1x |
| Reply to a customer email | 0.25¢ | 0.22¢ | 1.2x |
| Write a 1,500-word blog post | 1.5¢ | 0.47¢ | 3.2x |
| Write 10 product descriptions | 1.2¢ | 0.19¢ | 6.6x |
| Translate 1,000 words | 1.9¢ | 0.75¢ | 2.6x |
| Proofread one page (500 words) | 0.51¢ | 0.26¢ | 2.0x |
| Summarize a 20-page PDF | 1.6¢ | 0.33¢ | 4.7x |
| Extract data from an invoice | 0.65¢ | 0.16¢ | 3.9x |
| Analyze a 200-row spreadsheet | 3.9¢ | 0.71¢ | 5.4x |
| Answer from 5 retrieved documents (RAG) | 1.2¢ | 0.25¢ | 4.8x |
| Classify 100 support tickets | 2.9¢ | 0.46¢ | 6.2x |
| Review 500 lines of code | 1.3¢ | 0.62¢ | 2.1x |
| Write a SQL query | 0.67¢ | 0.19¢ | 3.5x |
| Run a 50-step coding agent | 50¢ | 13¢ | 3.7x |
Specs and list prices
| Gemini 3.8 Flash | Mistral Small 4 | |
|---|---|---|
| Input per 1M | $0.82 | $0.15 |
| Output per 1M | $4.12 | $0.60 |
| Cached input per 1M | $0.083 | $0.015 |
| Context | 1M | 262K |
| Providers | 7 | 4 |
| Reasoning | always | default |
| LMArena Text | 1496 | - |
| Released | Sep 2, 2026 | Mar 16, 2026 |
FAQ
Is Gemini 3.8 Flash or Mistral Small 4 cheaper?
Mistral Small 4 is cheaper on 14 of 14 tasks and about 3.7x cheaper on average (geometric mean).
How much does Gemini 3.8 Flash cost compared to Mistral Small 4 per token?
Gemini 3.8 Flash: $0.82 input and $4.12 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.