visionMicrosoft
Phi-4 Multimodal
Microsoft's compact multimodal model handling text, image and audio understanding.
microsoft/phi-4-multimodal-instructTest it live
Live playgroundPhi-4 Multimodalin-browser demo
Phi-4 Multimodalin-browser demoTest Phi-4 Multimodal live
Send a message and watch the model respond. Multi-turn — it remembers the conversation.
More vision models
Llama 3.2 90B Vision
Meta
Large multimodal model for image understanding, document Q&A, charts and visual reasoning.
meta/llama-3.2-90b-vision-instructInput / 1M
$0.35
Output / 1M
$0.40
Llama 3.2 11B Vision
Meta
Lightweight vision-language model for fast image captioning, OCR and visual Q&A.
meta/llama-3.2-11b-vision-instructInput / 1M
$0.06
Output / 1M
$0.06