Perplexity text embeddings via pay-per-call MPP on Tempo L2
What it does
This endpoint provides access to Perplexity's embedding models through the Locus MPP (Micropayment Protocol) gateway. It accepts text input and returns vector embeddings using Perplexity's proprietary embedding models: `pplx-embed-v1-0.6b` (a smaller, faster model) and `pplx-embed-v1-4b` (a larger, higher-quality model). Payment is settled per-call on Tempo L2 using pathUSD at approximately $0.001 per request.
The endpoint is part of a broader Perplexity service suite hosted on the same MPP gateway that also exposes Sonar chat (with web grounding), web search, and contextualized embeddings. The embeddings endpoint itself accepts a POST with a JSON body containing the model identifier and the input text (a single string or an array of strings). The OpenAPI spec lists the path as `/perplexity/embed`.
Note that the probe did not receive a 402 challenge when hitting this specific endpoint with HEAD/GET — it returned 404 instead. This is expected behavior for a POST-only endpoint on the Locus MPP gateway; the 404 on non-POST methods does not indicate the endpoint is down. The OpenAPI schema published by the gateway documents the endpoint as live with a 402 payment flow on POST. Documentation is available at the Perplexity API reference and the Locus skill file.
Capabilities
Use cases
- —Generating text embeddings for semantic search indexes
- —Computing similarity scores between documents or queries
- —Building retrieval-augmented generation (RAG) pipelines with Perplexity vectors
- —Clustering or classifying text passages by meaning
Fit
Best for
- —Agents needing pay-per-call embedding generation without API key management
- —Developers who want Perplexity-quality embeddings settled via crypto micropayments
- —RAG pipelines that need on-demand embedding computation
Not for
- —High-volume batch embedding jobs where a direct API key subscription would be cheaper
- —Use cases requiring image or multimodal embeddings
- —Applications that need streaming or real-time incremental embedding updates
Quick start
curl -X POST https://perplexity.mpp.paywithlocus.com/perplexity/embed \
-H "Content-Type: application/json" \
-d '{
"model": "pplx-embed-v1-0.6b",
"input": "The quick brown fox jumps over the lazy dog."
}'Example
Request
{
"input": "The quick brown fox jumps over the lazy dog.",
"model": "pplx-embed-v1-0.6b"
}Endpoint
Quality
The OpenAPI schema provides clear request structure, model options, and approximate pricing (~$0.001 per call). However, the probe did not capture a live 402 challenge on this specific endpoint (POST-only route returns 404 on HEAD/GET), no example response is available, and crawled pages all returned generic 404 JSON. Documentation links exist but were not crawled.
Warnings
- —Probe returned 404 on HEAD and GET — endpoint is POST-only; liveness via POST not confirmed in probe
- —No example response schema or sample output available
- —Approximate pricing (~$0.001) is stated in OpenAPI x-payment-info description but no exact amount or decimals were captured in a 402 challenge
- —Currency address 0x20c000000000000000000000b9537d11c60e8b50 is listed but not independently verified as pathUSD
Citations
- —Embedding models offered are pplx-embed-v1-0.6b and pplx-embed-v1-4bhttps://perplexity.mpp.paywithlocus.com
- —Approximate cost per embedding call is ~$0.001https://perplexity.mpp.paywithlocus.com
- —Payment settles via Tempo method using pathUSDhttps://perplexity.mpp.paywithlocus.com
- —API reference available at docs.perplexity.aihttps://docs.perplexity.ai
- —Locus MPP documentation at beta.paywithlocus.com/mpp/perplexity.mdhttps://beta.paywithlocus.com/mpp/perplexity.md