@juspay/neurolink
Version:
The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002
7 lines (6 loc) • 325 B
JavaScript
/** These metadata endpoints finish as HTTP responses, without model generation. */
export function isProxyAuxiliaryRequest(method, path) {
return ((method === "POST" && path === "/v1/messages/count_tokens") ||
(method === "GET" &&
(path === "/backend-api/codex/models" || path === "/v1/models")));
}