Mistral's Ministral 3 14B Reasoning 2512 is a powerful, open-source language model with vision capabilities, particularly suited for math, coding, and STEM-related tasks due to its post-training for reasoning tasks. It boasts a large context window of 262,144 tokens, allowing it to process extensive inputs.
Input
Output
Context
262K
Max Output
33K
Parameters
13.9B
Input Modalities
Output Modalities
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Automatically route workloads to the right model for every task, every time.