Mistral: Magistral Small 2506
mistralai/magistral-small-2506
Created Jun 10, 202540,960 context
$0.10/M input tokens$0.30/M output tokens
Magistral Small is a 24B parameter instruction-tuned model based on Mistral-Small-3.1 (2503), enhanced through supervised fine-tuning on traces from Magistral Medium and further refined via reinforcement learning. It is optimized for reasoning and supports a wide multilingual range, including over 20 languages.