Skip to main content
Models/Mistral AI/Magistral Small

Magistral Small

Mistral AI 🧠 Language Model

Efficient reasoning model for everyday logic tasks.

Specifications

Input modalitiestext
Output modalitiestext
Capabilitieschat, reasoning
Relative speed●●●●○ Fast
Context window131,072 tokens
Max output40,000 tokens
Vision inputNo
Tool callingNo
Streaming outputYes
Input price$0.875 / 1M
Output price$2.62 / 1M

Pricing

$0.875 / 1M input tokens  ·  $2.62 / 1M output tokens

Platform credit pricing — live rates on the Models page.

Use Magistral Small on Zubnet →

More from Mistral AI

M
Mistral Large 3
Open-weight flagship. 675B MoE (41B active), multimodal with vision. Apache 2.0 licensed.
🧠 Language Model
M
Mistral Small
Fast and efficient model for simple tasks. Great balance of performance and cost.
🧠 Language Model
C
Codestral
Specialized model for code generation, completion, and understanding.
🧠 Language Model
M
Mistral Medium
Premier frontier-class multimodal model. Great balance between Large and Small.
🧠 Language Model