checklist.day

Voyage Multimodal 3

JSON →
voyageai embedding
textimage

A multimodal embedding model that encodes both text and images into a shared vector space for cross-modal retrieval.

Specs

context window 32K tokens
input price $0.12 / 1M tokens

Capabilities

streaming

Dates

releasedJan 2024

Resources

homepagedocs.voyageai.com/docs/embeddings ↗
docsdocs.voyageai.com/reference/embeddings-api ↗

API

full doc /v1/models/voyage-multimodal-3