Perplexity Launches pplx-embed-v2-late Embedding Models for Text and Image Retrieval

Perplexity has released pplx-embed-v2-late, two late-interaction embedding models of 0.6B and 9B parameters that handle text-to-text and text-to-image retrieval in one shared space. Both checkpoints are on Hugging Face and work with sentence-transformers and transformers. The company says the smaller model matches systems with five times its active parameters on the ViDoRe (V3) benchmark.

• Perplexity launches pplx-embed-v2-late on Oct 7, 2026, a family of late-interaction embedding models handling text-to-text and text-to-image retrieval in a shared embedding space.
• Perplexity says the 0.6B model matches models with five times as many active parameters on the ViDoRe (V3) visual document retrieval benchmark.
• The two models, 0.6B and 9B, are distilled from an 18B teacher trained on 186 million query-document pairs from 594 datasets in 46 languages.