@juspay/neurolink/dist/models/manifests/perplexityDecider.d.ts

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

import type { ProviderModelManifest } from "../../types/index.js";
/**
 * Perplexity Decisions API — the `decide` inference type, not text generation,
 * and not the Sonar models of the `perplexity` text provider.
 *
 * `contextWindow` is the documented ceiling on input tokens per request,
 * shared by the state, every question and every image. `vision` describes
 * `generate()` input, which this provider does not serve; its image input is
 * `DecisionRequest.images`.
 *
 * `maxOutputTokens` is required by the manifest type but has no honest value
 * for a model that emits no text, so a small non-zero figure is used.
 */
export declare const perplexityDeciderManifest: ProviderModelManifest;