@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
19 lines (18 loc) • 535 B
JavaScript
/**
* Minimal manifest: groq has no MODEL_REGISTRY entries today, so
* only the provider-wide fallback is known. Named models can be added here
* incrementally without touching any consumer — see Task 5 of the model
* metadata consolidation plan.
*/
export const groqManifest = {
defaultContextWindow: 128000,
models: {
_default: {
aliases: [],
contextWindow: 128000,
maxOutputTokens: 64000,
vision: false,
functionCalling: false,
},
},
};