---
id: "perplexity/pplx-embed-v1-0.6b"
also: ["perplexity/pplx-embed-v1-0.6B", "vercel/perplexity/pplx-embed-v1-0.6b"]
card_usd_per_m: "0.004 in, 0.0 out, at perplexity/int8"
cheapest_list_usd_per_m: "0.004 in, 0.0 out, at perplexity/int8 on openrouter"
cheapest_effective_usd_per_m: "0.0039 in, 0.0 out, at perplexity/int8 on openrouter"
context: 32000
max_output: 28800
input: ["text"]
output: ["embeddings"]
released: "2026-03-16"
api: ["/api/v1/embeddings"]
params: ["max_tokens", "stop", "temperature"]
endpoints: 2
gateways: "openrouter (1), vercel (1)"
no_training: 1
trains: 0
retains_prompts: 0
---
# 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...