# Introducing pplx-embed — State-of-the-Art Embedding Models for Web-Scale Retrieval

**URL:** <https://community.perplexity.ai/t/introducing-pplx-embed-state-of-the-art-embedding-models-for-web-scale-retrieval/4732>\
**Category:** Announcements\
**Created:** [February 26, 2026, 10:00am UTC](https://community.perplexity.ai/t/introducing-pplx-embed-state-of-the-art-embedding-models-for-web-scale-retrieval/4732 "2026-02-26T10:00:00Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Kesku](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/kesku/32/898_2.png) [@Kesku](https://community.perplexity.ai/u/Kesku)\
**Post date:** [February 26, 2026, 10:00am UTC](https://community.perplexity.ai/t/introducing-pplx-embed-state-of-the-art-embedding-models-for-web-scale-retrieval/4732/1 "2026-02-26T10:00:00Z")

</div>

We’re releasing two embedding model families today: **pplx-embed-v1** and **pplx-embed-context-v1**.

These are built specifically for real-world, web-scale retrieval — the same kind of retrieval that powers Perplexity search. Open weights under MIT license on [Hugging Face](https://huggingface.co/collections/perplexity-ai/pplx-embed), and available now via the API.

### Models

| Model | Dimensions | Price ($/1M tokens) | Best For |
| --- | --- | --- | --- |
| `pplx-embed-v1-0.6b` | 1024 | $0.004 | Cost-efficient semantic search |
| `pplx-embed-v1-4b` | 2560 | $0.030 | High-accuracy retrieval |
| `pplx-embed-context-v1-0.6b` | 1024 | $0.008 | RAG with passage disambiguation |
| `pplx-embed-context-v1-4b` | 2560 | $0.050 | Production RAG pipelines |

### Standard Embeddings

```python
from perplexity import Perplexity

client = Perplexity()
response = client.embeddings.create(
    model="pplx-embed-v1-4b",
    input=["Hello world", "Another text"]
)
print(response.data[0].embedding)

```

### Contextualized Embeddings (for RAG)

The `pplx-embed-context` models disambiguate passages using surrounding document context — meaning chunks that share ambiguous terms get distinct embeddings based on their actual meaning in context.

```python
response = client.embeddings.create(
    model="pplx-embed-context-v1-4b",
    input=[
        ["Doc A chunk 1", "Doc A chunk 2"],
        ["Doc B chunk 1", "Doc B chunk 2"]
    ]
)

```

### Technical Highlights

- Built on diffusion-pretrained Qwen3 architecture with bidirectional attention
- No instruction prefix required — just pass your text
- MRL dimension reduction, INT8/BINARY quantization supported
- 32K token context window
- **81.96% on ConTEB benchmark** (vs Voyage voyage-context-3 at 79.45%)

### Get Started

- [Embeddings Quickstart](https://docs.perplexity.ai/docs/embeddings/quickstart)
- [API Reference](https://docs.perplexity.ai/api-reference/embeddings-post)
- [Contextualized Embeddings Reference](https://docs.perplexity.ai/api-reference/contextualized-embeddings-post)
- [Research Paper](https://research.perplexity.ai)
- [Open Weights on Hugging Face](https://huggingface.co/collections/perplexity-ai/pplx-embed)