@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, ~$0.00002
180 lines (179 loc) • 9.81 kB
JSON
{
"$schema": "./provider-catalog.schema.json",
"id": "neuralwatt",
"displayName": "Neuralwatt",
"aliases": [],
"tier": 2,
"wire": {
"baseURL": "https://api.neuralwatt.com/v1"
},
"models": {
"default": "glm-5.3",
"fallbacks": [
"glm-5.3-flash",
"qwen-3.8-27b",
"qwen3.6-35b",
"kimi-k2.7-code",
"kimi-k3",
"deepseek-v4.1-flash",
"gemma-4-31b"
],
"defaultContextWindow": 1048560,
"defaultMaxOutputTokens": 4096,
"visionModel": "qwen-3.8-27b",
"catalog": {
"glm-5.3": {
"contextWindow": 1048560,
"pricingPerMTok": {
"input": 1.45,
"output": 4.5,
"cachedInput": 0.145
},
"vision": false,
"status": "production",
"description": "ZhipuAI GLM 5.3 (fp8-native, zai-org/GLM-5.3) — the model used in every quickstart code sample on https://docs.neuralwatt.com/quickstart (curl, Python and Node.js all default to \"glm-5.3\"), so it is treated as Neuralwatt's own recommended default here. Roster metadata (GET /v1/models, 2026-09-28) marks reasoning mandatory (default effort \"max\") and declares tools:true and json_mode:true, but neither claim was independently probed — this onboarding is fully credential-free, no POST request was made. json_mode is not backed by a documented `response_format` parameter anywhere in the chat-completions API reference (https://docs.neuralwatt.com/api-reference/inference/create-a-chat-completion, retrieved 2026-09-28), so capabilities.structuredOutput is left false rather than trusting the flag alone. limits.max_output_tokens is null for this model in the live roster — omitted here rather than invented; models.defaultMaxOutputTokens (4096) is a generic placeholder, not a Neuralwatt-stated ceiling for this model. Pricing per the same roster response: $1.45 / $4.50 per MTok input/output, $0.145 cached input."
},
"glm-5.3-flash": {
"contextWindow": 1048560,
"pricingPerMTok": {
"input": 0.15,
"output": 0.5,
"cachedInput": 0.03
},
"vision": true,
"status": "production",
"description": "ZhipuAI GLM 5.3 Flash — lighter/cheaper sibling of the default. Roster-listed only (GET /v1/models, 2026-09-28); not itself exercised in any code sample; fallback. vision:true and max_output_tokens are as declared by the roster response — the latter is null there, so it is omitted rather than invented."
},
"qwen-3.8-27b": {
"contextWindow": 262128,
"maxOutputTokens": 131072,
"pricingPerMTok": {
"input": 0.45,
"output": 3.2,
"cachedInput": 0.25
},
"vision": true,
"status": "production",
"description": "Qwen 3.8 27B (Qwen/Qwen3.8-27B-FP8) — dense 27B VL model with native 262K context; the first entry in Neuralwatt's own /v1/models roster (GET, 2026-09-28) and one of the few catalog entries with a documented max_output_tokens ceiling (131,072) and image limits (max_images:20, max_images_total:200), so it is used as models.visionModel. Roster-listed and roster-priced only; fallback, not capability-probed (credential-free onboarding, no POST made)."
},
"qwen3.6-35b": {
"contextWindow": 262128,
"pricingPerMTok": {
"input": 0.29,
"output": 1.15,
"cachedInput": 0.029
},
"vision": true,
"status": "production",
"description": "Qwen 3.6 35B — roster-listed only (GET /v1/models, 2026-09-28); not capability-probed; fallback. max_output_tokens is null in the roster response, so it is omitted here."
},
"kimi-k2.7-code": {
"contextWindow": 262128,
"pricingPerMTok": {
"input": 0.95,
"output": 4.0,
"cachedInput": 0.095
},
"vision": true,
"status": "production",
"description": "MoonshotAI Kimi K2.7 Code (moonshotai/Kimi-K2.7-Code) — \"quant-agnostic canonical name for the Kimi K2.7 Code family\" per the roster's own description field (GET /v1/models, 2026-09-28). Roster-listed and roster-priced only; not capability-probed; fallback. max_output_tokens is null in the roster response, so it is omitted here."
},
"kimi-k3": {
"contextWindow": 1048560,
"pricingPerMTok": {
"input": 3.0,
"output": 15.0,
"cachedInput": 0.3
},
"vision": true,
"status": "production",
"description": "MoonshotAI Kimi K3 — general-purpose sibling of the Code line, 1M context per the roster (GET /v1/models, 2026-09-28). Roster-listed only; not capability-probed; fallback. max_output_tokens is null in the roster response, so it is omitted here."
},
"deepseek-v4.1-flash": {
"contextWindow": 1048560,
"maxOutputTokens": 393216,
"pricingPerMTok": {
"input": 0.15,
"output": 0.6,
"cachedInput": 0.015
},
"vision": true,
"status": "production",
"description": "DeepSeek V4.1 Flash — roster-listed with a documented max_output_tokens ceiling (393,216) and vision:true (GET /v1/models, 2026-09-28). Not capability-probed; fallback."
},
"gemma-4-31b": {
"contextWindow": 262128,
"maxOutputTokens": 16384,
"pricingPerMTok": {
"input": 0.144,
"output": 0.42,
"cachedInput": 0.0144
},
"vision": true,
"status": "production",
"description": "NVIDIA's Gemma 4 31B build (owned_by/provider \"nvidia\" per the roster, GET /v1/models, 2026-09-28) — the only catalog entry from that provider label. Roster-listed with a documented max_output_tokens ceiling (16,384); not capability-probed; fallback."
}
},
"topModels": [
"glm-5.3",
"glm-5.3-flash",
"qwen-3.8-27b",
"qwen3.6-35b",
"kimi-k2.7-code",
"kimi-k3",
"deepseek-v4.1-flash",
"gemma-4-31b"
]
},
"capabilities": {
"text": true,
"streaming": true,
"tools": "model-dependent",
"toolsWithStreaming": false,
"structuredOutput": false,
"structuredOutputWithTools": false,
"embeddings": false,
"thinking": true
},
"errorRules": [
{
"status": 401,
"pattern": "Invalid API key|invalid_api_key|authentication_error",
"class": "authentication",
"message": "Invalid Neuralwatt API key. Check {apiKeyEnvVar}. Get one at {setupUrl}"
},
{
"status": 404,
"pattern": "model_not_found|not\\s+found",
"class": "invalid-model",
"message": "Neuralwatt model '{model}' not found. Pick a current model from the unauthenticated GET https://api.neuralwatt.com/v1/models roster or {setupUrl}"
},
{
"status": 429,
"pattern": "rate_limit_exceeded|concurrent_budget_exceeded|tpm_uncached_exceeded",
"class": "rate-limit",
"message": "Neuralwatt rate limit hit for {model}. The error body includes retry_after and a retry_strategy — back off and retry rather than failing immediately."
}
],
"setup": {
"url": "https://portal.neuralwatt.com",
"apiKeyFormat": null,
"billingPolicy": "free-with-card",
"instructions": [
"1. Visit: https://portal.neuralwatt.com and sign up",
"2. Add a payment method in Dashboard > Billing — new accounts start with a $0 balance, and adding a card grants $1.00 in free trial credit (no charge is made; the credit is valid for 30 days)",
"3. Navigate to Dashboard > API Keys and create a new key — copy it immediately, it is shown in full only once and starts with sk-",
"4. Set {apiKeyEnvVar} in your .env file"
],
"description": "OpenAI-compatible endpoint at https://api.neuralwatt.com/v1 (\"Neuralwatt Cloud\"), serving 21 hosted open-weight models across Qwen, MoonshotAI Kimi, ZhipuAI GLM, DeepSeek and an NVIDIA Gemma build, with per-request energy and cost reporting (SSE comment lines / X-Request-Cost-USD headers). New accounts start at a $0 balance; adding a payment method grants a $1.00 trial credit valid 30 days, then usage is pay-per-token. Not all models support tool calling per Neuralwatt's own tool-calling guide — check a given model's capabilities on the /v1/models roster before relying on it."
},
"evidence": {
"rosterVerified": {
"date": "2026-09-28",
"method": "unauthenticated GET https://api.neuralwatt.com/v1/models — 21 models; credential-free, no key used",
"status": 200
},
"liveMatrix": null,
"addedInPR": "https://github.com/juspay/neurolink/pull/1848"
}
}