clip-ViT-B-32-multilingual-v1 · deepinfra

This model is a multilingual version of the OpenAI CLIP-ViT-B32 model, which maps text and images to a common dense vector space. It includes a text embedding model that works for 50+ languages and an image encoder from CLIP. The model was trained using Multilingual Knowledge Distillation, where a multilingual DistilBERT model was trained as a student model to align the vector space of the original CLIP image encoder across many languages.

Modelo baseTodos os modelos desta baseTodos os modelos do provedorao provedor

Todos os modelos Sentence Transformers em todos os provedores

Entrada, $/1M $0.005

Saída, $/1M —

Contexto 512

Aceita —

Última verificação 04.11.2026 12:00:14 UTC

Fonte —