@juspay/neurolink/dist/providers/catalog/koscompute.json

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

{
    "$schema": "./provider-catalog.schema.json",
    "id": "koscompute",
    "displayName": "Kosmik Compute",
    "aliases": [],
    "tier": 2,
    "wire": {
        "baseURL": "https://api.koscompute.com/v1"
    },
    "models": {
        "default": "qwen/qwen3.8-27b",
        "fallbacks": ["qwen/qwen3.8-27b"],
        "defaultContextWindow": 262144,
        "defaultMaxOutputTokens": 32768,
        "catalog": {
            "qwen/qwen3.8-27b": {
                "contextWindow": 262144,
                "maxOutputTokens": 32768,
                "pricingPerMTok": {
                    "input": 0.35,
                    "output": 2.2,
                    "cachedInput": 0.09
                },
                "vision": true,
                "status": "production",
                "description": "Qwen 3.8 27B (fp8) — the only chat-capable model in KosCompute's roster; the other 6 ids returned by /v1/models are Whisper transcription and TTS models (endpoint_kind audio/tts), not chat. Confirmed via unauthenticated GET https://api.koscompute.com/v1/models (2026-09-28, HTTP 200): context_length 262144 (modality_context_lengths.text), 131072 for image input; max_output_length/max_output 32768; pricing input $0.35 / output $2.20 per MTok, cached input $0.09 (the response's own precomputed input/output/cache_read fields, matching prompt/completion/input_cache_read per-token rates); supported_features [tool_calling, json_mode, structured_outputs, reasoning]; supported_endpoints [/v1/chat/completions, /v1/responses, /v1/messages]; input_modalities [text, image] with vision.max_pixels 1048576. model_info reports reasoning:true, extended_thinking:true, thinking_default:true, max_thinking_tokens:8192, supported_reasoning_efforts [none, low, medium, xhigh]. Docs corroborate generically for the chat-completions surface: api.koscompute.com/docs/guides/tool-calling/ (tools array, tool_choice auto|none|required|named, results read from choices[0].message.tool_calls), /docs/guides/structured-output/ (response_format json_object and json_schema, 'Unsupported models return a 400 capability error' for models lacking json_mode/structured_outputs — this model advertises both), and /docs/guides/streaming/ (stream:true, text/event-stream, data: [DONE]). No live capability probe was run (credential-free onboarding, no API key) — see evidence.liveMatrix: null."
            }
        },
        "topModels": ["qwen/qwen3.8-27b"]
    },
    "capabilities": {
        "text": true,
        "streaming": true,
        "tools": true,
        "toolsWithStreaming": true,
        "structuredOutput": true,
        "structuredOutputWithTools": false,
        "embeddings": false,
        "thinking": true
    },
    "errorRules": [
        {
            "status": 401,
            "class": "authentication",
            "message": "Invalid KosCompute API key. Check {apiKeyEnvVar}. See {setupUrl} for what KosCompute's docs publish on authentication — the vendor documents 401 as 'missing, invalid, expired, inactive, or conflicting credentials' but gives no example error body or code string."
        },
        {
            "status": 404,
            "pattern": "model_not_found",
            "class": "invalid-model",
            "message": "KosCompute model '{model}' not found. Pick a current id from an unauthenticated GET https://api.koscompute.com/v1/models."
        },
        {
            "status": 429,
            "pattern": "concurrent_limit_exceeded",
            "class": "rate-limit",
            "message": "KosCompute per-key concurrency limit exceeded for '{model}'. Wait for an in-flight request to finish, or reduce parallel requests, before retrying."
        }
    ],
    "setup": {
        "url": "https://api.koscompute.com/docs/overview/quickstart/",
        "apiKeyFormat": null,
        "billingPolicy": "no-free-tier",
        "instructions": [
            "1. KosCompute publishes no public signup, dashboard, or key-management page as of 2026-09-28 — the docs' quickstart (this URL) assumes you already hold a key and only shows how to use one, via `export KOSCOMPUTE_API_KEY=\"your-api-key\"`; the site's only 'Start building' call-to-action also points here, not to a signup form",
            "2. The docs reference an account 'balance' (/docs/overview/authentication/: 'Authentication success does not guarantee model access, remaining account balance, or available capacity') but publish no pricing, free-tier, or top-up page, so billing policy could not be confirmed from public sources — treat this entry's `no-free-tier` as the conservative default in the absence of any documented free allocation, not a confirmed vendor policy",
            "3. Once you have a key (provisioned out of band), set {apiKeyEnvVar} in your .env file",
            "4. Sanity-check connectivity first with an unauthenticated GET https://api.koscompute.com/v1/models (no key needed) before spending a real chat request"
        ],
        "description": "OpenAI-compatible endpoint at https://api.koscompute.com/v1, described by the vendor as EU-hosted inference (docs: 'EU-hosted, OpenAI-compatible inference for chat, reasoning, vision, speech recognition, and speech synthesis'); also exposes Responses-API and Anthropic-Messages-compatible surfaces for the same chat model. No public signup or key-management page is published, and billing policy is unconfirmed."
    },
    "evidence": {
        "rosterVerified": {
            "date": "2026-09-28",
            "method": "unauthenticated GET https://api.koscompute.com/v1/models — 7 models; credential-free, no key used",
            "status": 200
        },
        "liveMatrix": null,
        "addedInPR": "https://github.com/juspay/neurolink/pull/1848"
    }
}