# Perplexity releases open-weight pplx-embed-v2-context embedding models

> Original title: Introducing pplx-embed-v2-context: open-weight vision-language embedding models in 9B and 0.6B.

- Source: Perplexity Developers
- Published: 2026-11-02T21:50:52.000Z
- Bad Influence: https://badinfluence.news/items/oc7cz2va6aovmtor8zyhb4ikr
- Original: https://x.com/perplexitydevs/status/2117373903287050675

## Summary

Perplexity releases pplx-embed-v2-context, open-weight vision-language embedding models in 9B and 0.6B sizes. Both return one int8 vector per document, or one per chunk that sees the whole document.

## Post

Introducing pplx-embed-v2-context: open-weight vision-language embedding models in 9B and 0.6B.

Both return one int8 vector per document, or one per chunk that sees the whole document.

Read the paper, written with @turbopuffer: https://arxiv.org/abs/2610.38854

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWJsWC9akAEeBf4.png&mode=thumb&exp=1793923200&sig=5b0846e343fe15f0)