Ministral 3 14B Instruct 2512 API
About
Integrate multimodal vision capabilities using Ministral 3 14B Instruct 2512, designed to process both text and images seamlessly. This model delivers available completely free of charge, native tool calling support, open weights architecture. Access Ministral 3 14B Instruct 2512 via the Nvidia API with up to 16K output tokens.
Capabilities
Input Modalities
textimage
Output Modalities
text
Reasoning
No
Structured Output
Yes
Tool Use
Yes
WeightsOpen
Temperature
Adjustable
Attachment
Supported
Limits
Context Window
262K
Tokens
Input Limit
262K
Tokens
Max Output
16K
Tokens
Pricing
Standard (per 1M tokens)
Input
Free
Output
Free
Frequently Asked Questions
Ministral 3 14B Instruct 2512 by Nvidia costs Free per 1M input tokens and Free per 1M output tokens.
Model Details
ID
mistralai/ministral-14b-instruct-2512
Provider
NvidiaFamily
ministral
Release Date
Dec 2, 2025
Knowledge Cutoff
Dec 1, 2025
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
NVIDIA_API_KEY
API Base URL
https://integrate.api.nvidia.com/v1