@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, ~$0.00002
144 lines (143 loc) • 7.49 kB
JSON
{
"$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"
}
}