Embed v1 4b

perplexity/pplx-embed-v1-4b

An embedding model with a 32K-token context window, at $0.0315 per million tokens.

Details

Maker: perplexity
Kind: Embeddings
Context window: 32,000 tokens
Input: $0.0315 per million tokens
Capabilities: None listed
Takes: Text
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2026-02-26

Description

pplx-embed-v1 is a state-of-the-art text embedding model optimized for real-world, web-scale retrieval tasks.

Call it

curl

curl https://phantom.codes/v1/embeddings \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "perplexity/pplx-embed-v1-4b",
    "input": "The quick brown fox"
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model