Skip to main content

Ministral-3-14B-Instruct-2512

Description​

“Ministral-3-14B-Instruct-2512” is a multimodal, versatile chat model. It supports and is suitable for:

  • Text generation within a chat completion (text to text)
  • Image processing (image to text)
  • Tool-calling

The following limitations apply:

  • Maximum context length: 262,144 tokens
  • Maximum images per context: 4
  • Images must be submitted as Base64-encoded data URLs (no remote URLs)

It is recommended to operate the model with the following parameters:

  • temperature=0.1

For vision tasks, temperature=0.1 is recommended for accurate image description and text extraction. Always resize images to a maximum of 1024 px on the longest edge before encoding - large images significantly increase time to first token (TTFT). See the Python examples or JavaScript examples for a ready-to-use helper.

Terms of use and licensing​

The general terms of use apply. The model is provided under the Apache 2.0 License, and reuse of the generated content is not subject to any additional restrictions.