Skip to main content
Models/Mistral AI/Ministral 3 14B

Ministral 3 14B

Mistral AI 🧠 Language Model

High-performance edge model with vision. Best Ministral for complex tasks.

Specifications

Input modalitiestext, image
Output modalitiestext
Capabilitieschat, tools
Relative speed●●●●○ Fast
Context window131,072 tokens
Max output8,192 tokens
Vision inputYes
Tool callingYes
Streaming outputYes
Input price$0.35 / 1M
Output price$0.35 / 1M

Pricing

$0.35 / 1M input tokens  ·  $0.35 / 1M output tokens

Platform credit pricing — live rates on the Models page.

Use Ministral 3 14B 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
Magistral Small
Efficient reasoning model for everyday logic tasks.
🧠 Language Model