@juspay/neurolink/dist/providers/catalog/gmicloud.json

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

{
    "$schema": "./provider-catalog.schema.json",
    "id": "gmicloud",
    "displayName": "GMI Cloud",
    "aliases": ["gmi-cloud"],
    "tier": 2,
    "wire": {
        "baseURL": "https://api.gmi-serving.com/v1"
    },
    "models": {
        "default": "MiniMaxAI/MiniMax-M3",
        "fallbacks": ["MiniMaxAI/MiniMax-M3"],
        "defaultContextWindow": 1048576,
        "defaultMaxOutputTokens": 524288,
        "catalog": {
            "MiniMaxAI/MiniMax-M3": {
                "contextWindow": 1048576,
                "maxOutputTokens": 524288,
                "vision": false,
                "status": "production",
                "description": "MiniMaxAI/MiniMax-M3 — live GMI Cloud-probed model"
            }
        },
        "topModels": ["MiniMaxAI/MiniMax-M3"]
    },
    "capabilities": {
        "text": true,
        "streaming": true,
        "tools": true,
        "toolsWithStreaming": true,
        "structuredOutput": true,
        "structuredOutputWithTools": true,
        "embeddings": false,
        "thinking": false
    },
    "errorRules": [],
    "setup": {
        "url": "https://console.gmicloud.ai",
        "apiKeyFormat": "^eyJ[A-Za-z0-9_-]+\\.[A-Za-z0-9_-]+\\.[A-Za-z0-9_-]+$",
        "billingPolicy": "free-tier",
        "instructions": [
            "1. Visit: https://console.gmicloud.ai",
            "2. Sign in and select the Inference service",
            "3. Create an API key; check Console → Inference → Model Hub for current model pricing",
            "4. Set {apiKeyEnvVar} in your .env file"
        ]
    },
    "evidence": {
        "rosterVerified": {
            "date": "2026-09-03",
            "method": "authenticated GET /v1/models",
            "status": 200
        },
        "authProbe": {
            "date": "2026-09-03",
            "status": 401
        },
        "liveMatrix": {
            "date": "2026-09-03",
            "result": "MiniMax-M3 accepted max_completion_tokens=524288 and rejected 1048576 with an explicit 524288 limit. Structured output: the endpoint ignores response_format (json_schema and json_object both return prose with no prompt hint; raw fetch, 2026-09-03), so the SDK's structured-output fallback re-asks with the schema spelled out in the system prompt and coerces the reply — generate({ schema }) returned a schema-valid structuredData 3/3 in the prompt-fallback experiment and again in the final live proof through dist/index.js. structuredOutput and structuredOutputWithTools are declared true on that basis."
        },
        "addedInPR": "pending"
    }
}