@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, ~$0.00002
173 lines (172 loc) • 8.75 kB
JSON
{
"$schema": "./provider-catalog.schema.json",
"id": "inference-net",
"displayName": "Inference.net",
"aliases": [],
"tier": 2,
"wire": {
"baseURL": "https://api.inference.net/v1",
"envOverrides": {
"apiKey": "INFERENCE_API_KEY"
}
},
"models": {
"default": "glm-5.2",
"fallbacks": [
"glm-5.3",
"glm-5.3-flash",
"llama-3.3-70b-instruct",
"deepseek-v3.2",
"gpt-4.1-mini",
"gemini-2.5-flash",
"claude-haiku-4-5"
],
"defaultContextWindow": 1000000,
"defaultMaxOutputTokens": 128000,
"catalog": {
"glm-5.2": {
"contextWindow": 1000000,
"maxOutputTokens": 128000,
"pricingPerMTok": {
"input": 1.3,
"output": 4.4,
"cachedInput": 0.2
},
"vision": false,
"status": "production",
"description": "Zhipu GLM-5.2, served natively on Inference.net's own infrastructure. This is the exact model used in the request-body example on the vendor's own API quickstart (https://docs.inference.net/api/api-quickstart, retrieved 2026-09-28: `baseURL: \"https://api.inference.net/v1\"`, `model: \"glm-5.2\"`, streaming chat via the OpenAI SDK), so it is picked as the catalog default over an arbitrary roster pick. context_length/max_completion_tokens/pricing read from the live, unauthenticated GET https://api.inference.net/v1/models on 2026-09-28 (200, 63 models). input_modalities is [\"text\"] only for this model — no image/video support documented. Not live capability-probed (credential-free onboarding, no key used)."
},
"glm-5.3": {
"contextWindow": 1048576,
"maxOutputTokens": 131072,
"pricingPerMTok": {
"input": 0.9,
"output": 3.0,
"cachedInput": 0.15
},
"vision": false,
"status": "production",
"description": "Zhipu GLM-5.3 — newer GLM generation on the same live roster; one of only a handful of models whose supported_endpoints spans chat, responses and messages together (per the live /v1/models payload, 2026-09-28). input_modalities text-only. Roster-listed and priced from the vendor's own /v1/models response; not itself capability-probed."
},
"glm-5.3-flash": {
"contextWindow": 1048576,
"maxOutputTokens": 128000,
"pricingPerMTok": {
"input": 0.09,
"output": 0.28,
"cachedInput": 0.02
},
"vision": true,
"status": "production",
"description": "Zhipu GLM-5.3 Flash — cheapest model on the roster and the only one of the eight cataloged here whose live /v1/models entry lists input_modalities [\"text\",\"image\",\"video\"] (2026-09-28 GET), so it is the one model in this entry marked vision: true; not itself capability-probed end to end (no key used)."
},
"llama-3.3-70b-instruct": {
"contextWindow": 131072,
"maxOutputTokens": 128000,
"pricingPerMTok": {
"input": 0.13,
"output": 0.4
},
"vision": false,
"status": "production",
"description": "Meta Llama 3.3 70B Instruct, open-weight — widely-recognized baseline fallback. Roster-listed with no cached-input price on the live /v1/models payload (2026-09-28); input_modalities text-only."
},
"deepseek-v3.2": {
"contextWindow": 163840,
"maxOutputTokens": 65536,
"pricingPerMTok": {
"input": 0.7,
"output": 2.0,
"cachedInput": 0.35
},
"vision": false,
"status": "production",
"description": "DeepSeek V3.2, open-weight — roster-listed fallback from the live /v1/models GET (2026-09-28); input_modalities text-only."
},
"gpt-4.1-mini": {
"contextWindow": 1047576,
"maxOutputTokens": 32768,
"pricingPerMTok": {
"input": 0.4,
"output": 1.6,
"cachedInput": 0.1
},
"vision": true,
"status": "production",
"description": "OpenAI GPT-4.1 mini, reachable through Inference.net's hosted gateway under the same Bearer-key API (the vendor's quickstart separately documents a 'proxy mode' with extra x-inference-provider* headers for BYO provider keys — not used here; this catalog entry only relies on the plain gateway call). Live /v1/models (2026-09-28) lists input_modalities [\"text\",\"image\"], so marked vision: true; not capability-probed end to end."
},
"gemini-2.5-flash": {
"contextWindow": 1048576,
"maxOutputTokens": 65536,
"pricingPerMTok": {
"input": 0.3,
"output": 2.5,
"cachedInput": 0.03
},
"vision": true,
"status": "production",
"description": "Google Gemini 2.5 Flash, reachable through the same gateway. Live /v1/models (2026-09-28) lists input_modalities [\"text\",\"image\"], so marked vision: true; not capability-probed end to end."
},
"claude-haiku-4-5": {
"contextWindow": 200000,
"maxOutputTokens": 64000,
"pricingPerMTok": {
"input": 1.0,
"output": 5.0,
"cachedInput": 0.1
},
"vision": true,
"status": "production",
"description": "Anthropic Claude Haiku 4.5, reachable through the same gateway; the live /v1/models payload notes Claude-family entries list only the \"messages\" supported_endpoint (2026-09-28). input_modalities [\"text\",\"image\"], so marked vision: true; not capability-probed end to end."
}
},
"topModels": [
"glm-5.2",
"glm-5.3",
"glm-5.3-flash",
"llama-3.3-70b-instruct",
"deepseek-v3.2",
"gpt-4.1-mini",
"gemini-2.5-flash",
"claude-haiku-4-5"
]
},
"capabilities": {
"text": true,
"streaming": true,
"tools": true,
"toolsWithStreaming": false,
"structuredOutput": true,
"structuredOutputWithTools": false,
"embeddings": false,
"thinking": false
},
"errorRules": [
{
"status": 401,
"class": "authentication",
"message": "Invalid Inference.net API key. Check {apiKeyEnvVar}. Get one at {setupUrl}"
}
],
"setup": {
"url": "https://inference.net/register/",
"apiKeyFormat": null,
"billingPolicy": "free-tier",
"instructions": [
"1. Visit: https://inference.net/register/ and sign up",
"2. Create an Inference.net project API key from the dashboard (this is the gateway key that goes in {apiKeyEnvVar} — do not confuse it with a third-party provider key used only for the separate 'proxy mode')",
"3. New accounts start on a pay-as-you-go, $0-usage tier (1M included gateway requests/month, 30 req/min) per https://inference.net/pricing; confirm current terms before heavy use",
"4. Set {apiKeyEnvVar} in your .env file"
],
"description": "OpenAI-compatible endpoint at https://api.inference.net/v1 (`Authorization: Bearer <key>`), serving 63 models on the live roster across many upstream families — Claude, GPT, Gemini, DeepSeek, GLM, Kimi, Llama, Qwen, Gemma, Nemotron, plus Inference.net's own Schematron structured-extraction models — behind one API. A separate 'proxy mode' can forward to your own provider key via x-inference-provider* headers; not used by this catalog entry."
},
"evidence": {
"rosterVerified": {
"date": "2026-09-28",
"method": "unauthenticated GET https://api.inference.net/v1/models — 63 models; credential-free, no key used",
"status": 200
},
"liveMatrix": null,
"addedInPR": "https://github.com/juspay/neurolink/pull/1848"
}
}