{
    "$schema": "./provider-catalog.schema.json",
    "id": "empiriolabs",
    "displayName": "EmpirioLabs AI",
    "aliases": [],
    "tier": 2,
    "wire": {
        "baseURL": "https://api.empiriolabs.ai/v1"
    },
    "models": {
        "default": "glm-5-3",
        "fallbacks": [
            "glm-5-3-flash",
            "glm-5-2",
            "kimi-k3",
            "qwen3-7-max",
            "minimax-m2-7-highspeed"
        ],
        "defaultContextWindow": 1000000,
        "defaultMaxOutputTokens": 131072,
        "catalog": {
            "glm-5-3": {
                "contextWindow": 1000000,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 1.4,
                    "output": 4.4,
                    "cachedInput": 1.4
                },
                "vision": false,
                "status": "production",
                "description": "Recommended — EmpirioLabs' own roster marks this is_featured=true (GET /v1/models, 2026-09-28). Zhipu GLM-5.3: reasoning model with native function calling and web search, response_format json_object structured output, 1M token context, 131,072 token max output — all read directly from the unauthenticated GET https://api.empiriolabs.ai/v1/models. Pricing from the same roster: $1.40 / $4.40 per MTok input/output, $1.40 per MTok cached input. Onboarded credential-free — no live chat, streaming or tool-call request was made, so wire behavior (SSE framing, a real tool_call round-trip, image input) is roster- and docs-verified only, not live-probed; see evidence.liveMatrix (null)."
            },
            "glm-5-3-flash": {
                "contextWindow": 1000000,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 0.075,
                    "output": 0.25,
                    "cachedInput": 0.075
                },
                "vision": true,
                "status": "production",
                "description": "Zhipu GLM-5.3 Flash — lighter/cheaper sibling of the default. The roster marks capabilities.images=true (also video_understanding and document_understanding features), function calling and json_object structured output. 1M context, 131,072 max output. Pricing: $0.075 / $0.25 per MTok input/output, $0.075 cached. Roster-listed only, not capability-probed (credential-free onboarding — no live request made); fallback."
            },
            "glm-5-2": {
                "contextWindow": 1000000,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 1.4,
                    "output": 4.4,
                    "cachedInput": 1.4
                },
                "vision": false,
                "status": "production",
                "description": "Zhipu GLM-5.2 — prior GLM generation; reasoning, function calling, web search; json_object structured output; 1M context, 131,072 max output. Pricing $1.40 / $4.40 per MTok. Roster-listed only, not capability-probed; fallback."
            },
            "kimi-k3": {
                "contextWindow": 1000000,
                "maxOutputTokens": 131072,
                "pricingPerMTok": {
                    "input": 3,
                    "output": 15,
                    "cachedInput": 3
                },
                "vision": true,
                "status": "production",
                "description": "Moonshot Kimi K3 — reasoning, function calling, multimodal (capabilities.images=true on the roster), agentic coding and web search; strict json_schema structured output (a stronger guarantee than glm-5-3's json_object). 1M context, 131,072 max output. Pricing $3 / $15 per MTok. Roster-listed only, not capability-probed; fallback."
            },
            "qwen3-7-max": {
                "contextWindow": 1000000,
                "maxOutputTokens": 65536,
                "pricingPerMTok": {
                    "input": 2.5,
                    "output": 7.5,
                    "cachedInput": 2.5
                },
                "vision": false,
                "status": "production",
                "description": "Alibaba Qwen3.7 Max — flagship text reasoning model with code_interpreter, function calling and agentic coding; strict json_schema structured output. 1M context, 65,536 max output (lower than the GLM family's 131,072 — read from the roster, not assumed). Pricing $2.50 / $7.50 per MTok. Roster-listed only, not capability-probed; fallback."
            },
            "minimax-m2-7-highspeed": {
                "contextWindow": 200000,
                "maxOutputTokens": 32768,
                "pricingPerMTok": {
                    "input": 0.3,
                    "output": 1.2,
                    "cachedInput": 0.03
                },
                "vision": false,
                "status": "production",
                "description": "MiniMax M2.7 Highspeed — reasoning and function calling only (no vision or web_search declared on the roster); json_object structured output. Smallest context in this curated set (200K, 32,768 max output) — kept as the lightest/cheapest fallback. Pricing $0.30 / $1.20 per MTok, $0.03 cached. Roster-listed only, not capability-probed; fallback."
            }
        },
        "topModels": [
            "glm-5-3",
            "glm-5-3-flash",
            "glm-5-2",
            "kimi-k3",
            "qwen3-7-max",
            "minimax-m2-7-highspeed"
        ],
        "visionModel": "glm-5-3-flash"
    },
    "capabilities": {
        "text": true,
        "streaming": true,
        "tools": "model-dependent",
        "toolsWithStreaming": false,
        "structuredOutput": true,
        "structuredOutputWithTools": false,
        "embeddings": false,
        "thinking": false
    },
    "errorRules": [
        {
            "status": 401,
            "class": "authentication",
            "message": "Invalid EmpirioLabs API key. Check {apiKeyEnvVar}. Get one at {setupUrl}"
        }
    ],
    "setup": {
        "url": "https://platform.empiriolabs.ai",
        "apiKeyFormat": "^sk-empiriolabs-",
        "billingPolicy": "free-tier",
        "instructions": [
            "1. Visit: https://platform.empiriolabs.ai and create an account",
            "2. Create an API key from the dashboard (keys use the sk-empiriolabs- prefix, up to 50 per account)",
            "3. Selected models (e.g. GLM 4.7 Flash) run at $0 cost; other models draw from prepaid credits topped up via the dashboard Billing page — confirm current pricing before heavy use",
            "4. Set {apiKeyEnvVar} in your .env file"
        ],
        "description": "OpenAI-compatible endpoint at https://api.empiriolabs.ai/v1 (docs.empiriolabs.ai confirms it accepts the OpenAI Chat Completions request format). Hosts a large catalog — 217 models on an unauthenticated GET /v1/models as of 2026-09-28 — spanning text, vision, audio, video, image and 3D generation; this catalog entry covers only a curated set of text/chat-completions-capable models. New accounts default to 50 RPM / 2,000,000 TPM."
    },
    "evidence": {
        "rosterVerified": {
            "date": "2026-09-28",
            "method": "unauthenticated GET https://api.empiriolabs.ai/v1/models — 217 models; credential-free, no key used",
            "status": 200
        },
        "liveMatrix": null,
        "addedInPR": "https://github.com/juspay/neurolink/pull/1848"
    }
}