{
    "$schema": "./provider-catalog.schema.json",
    "id": "llmtech",
    "displayName": "LLM Tech",
    "aliases": [],
    "tier": 2,
    "wire": {
        "baseURL": "https://api.llmtech.eu/v1"
    },
    "models": {
        "default": "nvidia/Qwen3.8-27B-NVFP4",
        "fallbacks": ["nvidia/Qwen3.8-27B-NVFP4"],
        "defaultContextWindow": 262144,
        "defaultMaxOutputTokens": 32768,
        "catalog": {
            "nvidia/Qwen3.8-27B-NVFP4": {
                "contextWindow": 262144,
                "maxOutputTokens": 32768,
                "pricingPerMTok": {
                    "input": 0.25,
                    "output": 2.09,
                    "cachedInput": 0.04
                },
                "vision": true,
                "status": "production",
                "description": "LLM Tech's sole hosted chat model (NVFP4-quantized Qwen3.8-27B on Blackwell), self-hosted on EU hardware (GPU node in Italy, edge in Nuremberg). Re-verified live via unauthenticated GET https://api.llmtech.eu/v1/models on 2026-09-28 (HTTP 200, exactly 1 model): context_length 262144, max_output/max_output_tokens 32768, pricing_per_m input $0.25 / output $2.09 / cache_read $0.04 per MTok, and a features array of [tools, json_mode, structured_outputs, logprobs, reasoning, vision] on the model object itself. All of this matches the vendor's own model page (https://llmtech.eu/models/qwen3.8-27b, retrieved 2026-09-28), which documents: an OpenAI-compatible client.chat.completions.create(...) quickstart against this baseURL; SSE streaming ('SSE, OpenAI format', stream=True in the sample); tool calling ('yes, with structured outputs'); real vision support ('yes, the vision tower is kept in BF16 and works' — image tokens count toward prompt_tokens and bill at the input rate, e.g. a 64x64 PNG costs 64 image tokens; images must go in a user message, not a system message; the page notes third-party listings calling this model text-only are wrong); reasoning control via enable_thinking/reasoning_effort request parameters; automatic prompt caching billed at the cache rate; and zero data retention (prompts/completions 'never used for training'). No response_format wire example or combined tools+response_format request is shown or was probed (see capabilities.structuredOutputWithTools). Not itself capability-probed end to end — credential-free onboarding, no API key used."
            }
        },
        "topModels": ["nvidia/Qwen3.8-27B-NVFP4"]
    },
    "capabilities": {
        "text": true,
        "streaming": true,
        "tools": true,
        "toolsWithStreaming": false,
        "structuredOutput": true,
        "structuredOutputWithTools": false,
        "embeddings": false,
        "thinking": true
    },
    "errorRules": [],
    "setup": {
        "url": "https://llmtech.eu/models/qwen3.8-27b",
        "apiKeyFormat": null,
        "billingPolicy": "no-free-tier",
        "instructions": [
            "1. LLM Tech publishes no public signup or self-service key page as of 2026-09-28 (self-service is described on the vendor's site as 'planned'); email artem@llmtech.eu to request a key — the account dashboard (https://llmtech.eu/cabinet/) confirms keys are issued by the company rather than self-created ('we hold no passwords and no accounts'; 'paste the API key we issued you')",
            "2. Once you receive a key, https://llmtech.eu/cabinet/ shows current-month billing (totals, a daily usage chart, invoice line items) by pasting the key in — there is no separate account or login",
            "3. Billing is pay-per-token USD with 'no subscription, no minimums' (input $0.25/M, output $2.09/M, cached input $0.04/M per https://llmtech.eu/models/qwen3.8-27b); no free tier is documented, so budget for paid usage from the first call",
            "4. Set {apiKeyEnvVar} in your .env file"
        ],
        "description": "OpenAI-compatible endpoint at https://api.llmtech.eu/v1, self-hosted on EU hardware (GPU node in Italy, edge in Nuremberg), serving a single model — nvidia/Qwen3.8-27B-NVFP4 — confirmed live by an unauthenticated GET /v1/models. No public signup exists; keys are issued manually by the vendor via email. The vendor states zero data retention: prompts and completions are never used for training."
    },
    "evidence": {
        "rosterVerified": {
            "date": "2026-09-28",
            "method": "unauthenticated GET https://api.llmtech.eu/v1/models — 1 model; credential-free, no key used",
            "status": 200
        },
        "liveMatrix": null,
        "addedInPR": "https://github.com/juspay/neurolink/pull/1848"
    }
}