Mistral Small 3.1 vs Mistral Medium 3
Side-by-side comparison of pricing and capabilities
Mistral Small 3.1
Mistral Medium 3
Input Price Comparison
| Attribute | Mistral Small 3.1 | Mistral Medium 3 |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Input Price | $0.1 /1M tokens | $0.4 /1M tokens |
| Output Price | $0.3 /1M tokens | $2 /1M tokens |
| Cached Input | $0.010 /1M tokens | $0.040 /1M tokens |
| Context Window | 131K | 131K |
| Type | chat | chat |
| Status | current | current |
Capability Comparison
| Capability | Mistral Small 3.1 | Mistral Medium 3 |
|---|---|---|
| coding | ||
| multilingual | ||
| reasoning |
Which should you choose?
Budget-conscious: Mistral Small 3.1 is 75% cheaper on input tokens ($0.1 vs $0.4 per 1M tokens).
Context-heavy tasks: Both models offer the same context window size.
Capability fit: Mistral Small 3.1 supports 2 capabilities (coding, multilingual), while Mistral Medium 3 supports 3 (coding, reasoning, multilingual).
Frequently Asked Questions
Which is cheaper: Mistral Small 3.1 or Mistral Medium 3?
Mistral Small 3.1 costs $0.1/1M input vs Mistral Medium 3 at $0.4/1M input. Mistral Small 3.1 is 75% cheaper on input tokens.
How do output prices compare between Mistral Small 3.1 and Mistral Medium 3?
Mistral Small 3.1 output: $0.3/1M, Mistral Medium 3 output: $2/1M. Mistral Small 3.1 is more economical for generation-heavy workloads.
What is Mistral Small 3.1 best used for?
Mistral Small 3.1 is best for budget-conscious applications, high-volume chatbots, and tasks where cost efficiency is the primary concern.
What is Mistral Medium 3 best used for?
Mistral Medium 3 is suited for complex reasoning, analysis, and tasks that benefit from its coding and reasoning capabilities.