Mistral: Magistral Small 2506
Mistral • text • function-calling • json-mode
mistralai/magistral-small-2506Magistral 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.
Best For:
High-volume, low-latency tasks where cost efficiency is paramount
Pricing:
$0.00/1M input tokens, $0.00/1M output tokens
Context Window:
40,000 tokens
Key Differentiator:
Cost-optimized for high-volume usage