Perplexity: Embed V1 0.6B

Origin

perplexity/pplx-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...

Pricing

Input · 0.0048 MA / 1M tokens

Billing follows the provider's own reported cost. The unit prices here are for reference; a model marked "billed at actual usage" has no reliable pre-call price, so your usage page is the record of what you paid.

Call it

Embedding models are served on POST /v1/embeddings, with the same request and response shape as OpenAI's Embeddings API. input is a string or an array of strings, and each input gets one vector back.

curl https://macdecloud.com/v1/embeddings \
  -H "Authorization: Bearer dcld-sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"perplexity/pplx-embed-v1-0.6b","input":["first text","second text"]}'

Python (OpenAI SDK)

The official OpenAI SDK works as is; just point base_url at deCloud.

from openai import OpenAI

client = OpenAI(base_url="https://macdecloud.com/v1", api_key="dcld-sk-...")
resp = client.embeddings.create(model="perplexity/pplx-embed-v1-0.6b", input=["first text", "second text"])
print(len(resp.data), len(resp.data[0].embedding))