Mistral Small 4 vs Mistral Medium 3.5: standard utility vs balanced logic costs
Lightweight utility versus balanced medium-scale logic.
Balancing speed and quality often leads developers to compare Mistral Small 4 and Mistral Medium 3.5. Let's compare their cost structures.
Cost Comparison
Based on 100,000 input tokens (50% cached), 5,000 output tokens, and 100 requests.
Side-by-side specs
| Spec | Mistral Small 4 | Mistral Medium 3.5 |
|---|---|---|
| Input Cost (per M) | $0.15 (better on this spec) | $0.40 |
| Output Cost (per M) | $0.60 (better on this spec) | $2.00 |
| Cached Input (per M) | $0.015 (better on this spec) | $0.04 |
| Batch Discount | 50% | 50% |
How they differ
Mistral Small 4 costs $0.15 per million input tokens and $0.60 per million output tokens. Mistral Medium 3.5 is priced at $0.40 per million input tokens and $2.00 per million output tokens. Both support a 90% caching discount and a 50% batch discount.
Verdict
Mistral Small 4 is the clear budget winner. Use Mistral Medium 3.5 for tasks requiring a step up in translation or conversational quality without paying premium frontier prices.
Which should you pick?
Choose Mistral Small 4
Sentiment analysis, high-caching search routing, and standard text summaries.
Choose Mistral Medium 3.5
Intermediate multilingual text generation, conversational assistants, and detailed reports.