Wispr Flow - Don’t type, just speak
Mini tools| Model | Input | Cached input | Output | Unit |
|---|---|---|---|---|
|
pplx embed v1 0.6b
This model
Perplexity
|
$0.004 | - | $0 | per 1M tokens |
|
pplx embed v1 4b
Perplexity
|
$0.03 | - | $0 | per 1M tokens |
|
pplx embed context v1 0.6b
Perplexity
|
$0.008 | - | $0 | per 1M tokens |
|
pplx embed context v1 4B
Perplexity
|
$0.05 | - | $0 | per 1M tokens |
pplx embed v1 0.6b
By Perplexity
pplx-embed-v1-0.6b is a multilingual text embedding model with 0.6B parameters, part of the pplx-embed-v1 family. It uses a diffusion-pretrained Qwen3 backbone with bidirectional attention, enabling comprehensive contextual representations via mean pooling. The model produces 1024-dimensional embeddings natively quantized to int8 or binary (compared via cosine similarity unnormalized), with a 32K token context window and Matryoshka Representation Learning for variable-length dimensions. Designed for independent text embedding of queries and documents in standard retrieval and semantic search tasks. Deployable via the Perplexity API, SentenceTransformers, ONNX, or Text Embeddings Inference. Evaluated on MTEB(Multilingual v2), MTEB(Code), MIRACL, BERGEN, and ToolRet benchmarks. MIT licensed.
Text
Gen 7
Overview
A 0.6B parameter multilingual text embedding model built on a diffusion-pretrained Qwen3 backbone. Produces 1024-dimensional unnormalized embeddings with int8 and binary quantization support, a 32K token context window, and Matryoshka Representation Learning. Optimized for web-scale retrieval and semantic search.
Pricing
Compare pplx embed v1 0.6b with other models listed in the same vendor pricing tiers and context lengths.
Embeddings
About Perplexity
Perplexity is a technology company that specializes in artificial intelligence and machine learning solutions.
Industry:
Artificial Intelligence
Company Size:
247
Location:
San Francisco, California, US
Website:
perplexity.ai
Last updated: June 25, 2026
