{ "$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 `), 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" } }