Models
Phi-4-multimodal-instruct
4K max output
chat
Pricing
Per 1M tokens
Input
$0.08
Cached input
—
Output
$0.32
Cache write
—
Modalities
Input
text
Output
text
Features
Streaming
Function calling
Vision
Reasoning
JSON mode
Share This Model
Share on X or copy the link
Azure AI
Phi 4 Multimodal Instruct
Input
$0.08/M
Output
$0.32/M
Text Generation