Phi-4-multimodal-instruct · deepinfra

Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models. The model processes text, image, and audio inputs, generating text outputs, and comes with 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning, direct preference optimization and RLHF (Reinforcement Learning from Human Feedback) to support precise instruction adherence and safety measures. The languages that each modal supports are the following: - Text: Arabic, Chinese, Czech, Danish, Dutch, English, Finnish, French, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Russian, Spanish, Swedish, Thai, Turkish, Ukrainian - Vision: English - Audio: English, Chinese, German, French, Italian, Japanese, Spanish, Portuguese

Modelo baseTodos los modelos de esta baseTodos los modelos del proveedoral proveedor

Todos los modelos de Microsoft en todos los proveedores

Entrada, $/1M $0.05

Salida, $/1M $0.10

Contexto 131 072

Acepta —

Última comprobación 04.11.2026 12:00:14 UTC

Fuente —