@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
44 lines (43 loc) • 1.57 kB
JavaScript
/**
* Cloudflare Clef on Workers AI — the `decide` inference type, not text
* generation, and not the Workers AI text models of the `cloudflare` provider.
*
* `contextWindow` is the figure Cloudflare documents (65,536 tokens). The
* Workers AI endpoint ignored state text past about 2,048 tokens until
* 2026-10-04 and read far more on 2026-10-07 (hosted service or model:
* unknown), so NeuroLink enforces the limit on the descriptor's
* `decisionLimits`, not this. `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 const cloudflareClefManifest = {
defaultContextWindow: 65_536,
models: {
_default: {
aliases: [],
contextWindow: 65_536,
maxOutputTokens: 256,
vision: false,
functionCalling: false,
},
clef: {
aliases: ["@cf/cloudflare/clef"],
displayName: "Cloudflare Clef (27B)",
contextWindow: 65_536,
maxOutputTokens: 256,
vision: false,
functionCalling: false,
},
"clef-flash": {
aliases: ["@cf/cloudflare/clef-flash"],
displayName: "Cloudflare Clef-flash (9B)",
contextWindow: 65_536,
maxOutputTokens: 256,
vision: false,
functionCalling: false,
},
},
};