Cracked AI Engineering

Phi-4-multimodal-instruct

GitHub ModelsOpen Weights

The Phi-4-multimodal-instruct AI model by GitHub Models offers developers a powerful tool with a context window of 128,000 tokens and advanced reasoning capabilities. With support for text input, vision, audio, and function calling, this model is ideal for complex tasks requiring multimodal inputs. Open weights and competitive pricing make it a valuable resource for cutting-edge AI development projects.

Key Specifications

Context Window

128K tokens

Max Output Tokens

4K tokens

Input Pricing

Free

per million tokens

Output Pricing

Free

per million tokens

Capabilities

  • Text Generation
  • Vision
  • Audio Input
  • Function Calling
  • Advanced Reasoning

Additional Details

Release Date
December 11, 2024
Advanced Reasoning
Supported
Supported Input Types
text, image, audio

Compare with Similar Models