Skip to content
Dashboard

Embed v1 4b

Embed v1 4b is the higher-accuracy tier of Perplexity's pplx-embed-v1 text embedding family. It returns 2560-dimensional vectors quantized to INT8 natively, requires no instruction prefix, and accepts inputs up to 32K tokens. Your use is subject to Perplexity's Terms & Privacy Policies.

import { embed } from 'ai';
const result = await embed({
model: 'perplexity/pplx-embed-v1-4b',
value: 'Sunny day at the beach',
})
Read docs

More models by Perplexity

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
32K
$0.004/M
perplexity logo
02/26/2026
127K
2.1s
201tps
$1/M
$1/M
$5/K*+2 more
perplexity logo
02/19/2025
200K
1.4s
$3/M
$15/M
$6/K*+2 more
perplexity logo
02/19/2025
127K
4.2s
134tps
$2/M
$8/M
$6/K*+2 more
perplexity logo
02/19/2025