Mistral Medium 3 API
About
Integrate multimodal vision capabilities using Mistral Medium 3, designed to process both text and images seamlessly. This model delivers available completely free of charge. Access Mistral Medium 3 via the Nvidia API with up to 33K output tokens.
Capabilities
Input Modalities
textimage
Output Modalities
text
Reasoning
No
Structured Output
No
Tool Use
No
WeightsClosed
Temperature
Fixed
Attachment
Supported
Limits
Context Window
131K
Tokens
Input Limit
131K
Tokens
Max Output
33K
Tokens
Pricing
Standard (per 1M tokens)
Input
Free
Output
Free
Frequently Asked Questions
Mistral Medium 3 by Nvidia costs Free per 1M input tokens and Free per 1M output tokens.
Model Details
ID
mistralai/mistral-medium-3-instruct
Provider
NvidiaFamily
mistral-medium
Release Date
Sep 25, 2025
Knowledge Cutoff
N/A
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
NVIDIA_API_KEY
API Base URL
https://integrate.api.nvidia.com/v1