Perplexity's contextual embedding model Embed V2 Context (9B/0.6B) is live on OpenRouter

antoine_chaffin · x · 2026-11-21

Perplexity's Embed V2 Context multimodal embedding models are now available on OpenRouter in 9B and 0.6B sizes, covering text, images, and document pages.

Key feature: send a document as an ordered list of chunks and each chunk's embedding reflects the whole document — aimed at RAG and search pipelines. Returns 2048-dim vectors by default (1024 optional); both sizes share an embedding space so indexes built with one can be queried with the other. Priced at $0.12/M tokens with 32K context, and separate inputtype modes for queries vs documents.

Original post →

More from Models

Models channel →