@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, ~$0.00002
78 lines (77 loc) • 3.83 kB
JSON
{
"$schema": "./provider-catalog.schema.json",
"id": "aihubmix",
"displayName": "AIHubMix",
"enumTypeName": "AIHubMixModels",
"aliases": [],
"tier": 2,
"wire": {
"baseURL": "https://aihubmix.com/v1"
},
"models": {
"default": "gpt-4o-mini",
"fallbacks": ["gpt-4o-mini"],
"defaultContextWindow": 128000,
"defaultMaxOutputTokens": 16384,
"catalog": {
"gpt-4o-mini": {
"contextWindow": 128000,
"maxOutputTokens": 16384,
"vision": false,
"status": "production",
"description": "AIHubMix's paid GPT 4o Mini. Exact context/output limits and active lifecycle are published in its own model-page record on 2026-10-09. This pilot declares text generate/stream; tools, vision, strict schema and effort controls await separate evidence and acceptance. Account/model access is unverified."
}
}
},
"capabilities": {
"text": true,
"streaming": true,
"tools": false,
"toolsWithStreaming": false,
"structuredOutput": false,
"structuredOutputWithTools": false,
"embeddings": false,
"thinking": false
},
"errorRules": [
{
"status": 401,
"class": "authentication",
"message": "Invalid or expired AIHubMix API key. Check {apiKeyEnvVar} and your key permissions."
},
{
"pattern": "insufficient_user_quota|insufficient.*quota",
"patternStatuses": [403],
"class": "provider",
"message": "AIHubMix quota or paid-model access is insufficient. The gpt-4o-mini default is usage-priced; verify account funding and model eligibility."
},
{
"pattern": "model_retired|model.*retired",
"patternStatuses": [404],
"class": "invalid-model",
"message": "The requested AIHubMix model '{model}' is retired. Select a current documented model; gpt-4o-free and gpt-5.5-free are excluded from this pilot."
}
],
"setup": {
"url": "https://console.aihubmix.com",
"apiKeyFormat": null,
"billingPolicy": "free-tier",
"instructions": [
"1. Sign in to the AIHubMix console and create an API key.",
"2. The selected gpt-4o-mini default is paid and usage-priced. Verify your own account funding, model permissions and current rates before using it.",
"3. The vendor-level free-tier label refers to AIHubMix's separately documented, model-limited free programme. It does not grant free usage of gpt-4o-mini; current model eligibility and allowances are unverified.",
"4. Current model-specific guides mark gpt-4o-free and gpt-5.5-free retired. Do not use either as a default or fallback based on older free-model marketing.",
"5. Set {apiKeyEnvVar} for this provider. The documented base URL is https://aihubmix.com/v1."
],
"description": "AIHubMix gateway text/stream pilot with a paid gpt-4o-mini default. A separate model-limited free programme is documented; no account entitlement, roster, live inference or delivery is verified."
},
"evidence": {
"rosterVerified": {
"date": "2026-10-09",
"code": "PUBLIC_DOCS_ONLY_NOT_ROSTER_VERIFIED",
"method": "Public documentation GETs of https://aihubmix.com/model/gpt-4o-mini and its /llms.txt guide. Exact own model-page record binds context_window=128000 and max_output=16384. No vendor roster, auth, billing or inference probe ran; this legacy field does not assert roster verification."
},
"liveMatrix": null,
"addedInPR": "https://github.com/juspay/neurolink/pull/1966"
}
}