← All models

perplexity

Perplexity: Embed V1 0.6B

pplx-embed-v1-0.6B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 0.6B parameter model targeting lightweight, low-latency embedding generation.

Try in playgroundAPI reference
32,000 context
Modalities:text->embeddings
Released:3/15/2026

pplx-embed-v1-0.6B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 0.6B parameter model targeting lightweight, low-latency embedding generation.

Weekly tokens

6.8B

Tokens generated this week (network-wide)

Usage by period

Today215 tokens
This week3.4K tokens
This month31.3B tokens
Trending3.4K tokens