Mistral

Ministral 3

Small, dense multimodal model designed for efficient text and vision understanding with deployment-friendly performance.

Best for: Edge deployment, chat, instruction-following, multimodal analysis

Intelligence

75

Speed

80

Released

2025-12-02

Training cutoff

2025-08-01

Capabilities

  • ✓Temperature control
  • ✓Web search
  • ✓Image understanding
  • ✓File/document understanding
  • ✓Image generation(drawn by OpenAI, Gemini, Grok, Qwen, MiniMax or Meta — your pick)
Try Ministral 3 in EVA

We count visits anonymously, without cookies. Accept to also allow analytics cookies, session recordings, and limited sharing with Google to measure our ads. Our analytics never collect the content of your chats. Privacy Policy · Your Privacy Choices