https://agent.pocket.network/v1/semantic-similarity
Text and embedding similarity scoring: cosine match and dedupe decisions at fixed model precision. POST /v1/semantic with {text_a, text_b} and get a similarity score as one JSON object. Deterministic. Pay per request in USDC; no account, no API key.
What this profile is sourced from
Raw HTTP — what an agent observes
GET https://agent.pocket.network/v1/semantic-similarity → HTTP/1.1 402 Payment Required X-Payment-Required: $0.0050 X-Payment-Currency: USDC X-Payment-Chain: base GET https://agent.pocket.network/v1/semantic-similarity X-Payment: <signed-receipt> → HTTP/1.1 200 OK Content-Type: application/json …response body…
Things to know before drawing strong conclusions
accepts[] entry is used.