Linkworld Platform

EU-sovereign AI infrastructure.
Multi-LLM, metered per tenant.

Sovereign infrastructure the way you know it from European cloud providers — built for agentic AI: multi-LLM routing, tenant isolation with usage metering, an approval layer in front of every high-stakes action, and a complete audit trail. Consumable as the runtime for your apps or headless inside your product.

Create API key See app building

Self-service · billed per tenant & usage · no sales call required

Your apps & productsvisible to your users Agent orchestration Workflow-Engine Multi-LLM-Router Memory & RAG Tools via MCP Tenant isolation + metering Approval-Layer Audit-Trail

Multi-LLM, no lock-in

Best model per task — Claude, GPT, Mistral, open source. Provider outages fail over automatically.

Tenant isolation + metering

Every tenant runs isolated; all usage is metered per tenant — billing-ready for your business model.

Approval layer built in

A security gate in front of high-stakes actions: payments, outgoing mail, data access — only after approval.

EU operations, auditable

EU data centers, GDPR-native, EU-AI-Act-ready. Every action logged in a structured, exportable way.

Platform API · Sovereign models

EU-sovereign LLMs. Per token, on demand.

Open models, operated EU-sovereign under our control — including the best reasoning models, always in their latest version. Create an API key in your workspace, start building, billed per tenant. Frontier models run through the same router.

Model	Class		Input · € / 1M tokens	Output · € / 1M tokens
gpt-oss-120B	Reasoning — GPT open-weight: math, code, planning	EU-sovereign	€0.10	€0.48
Qwen 3.5 397B	Flagship — reasoning & vision, long context	EU-sovereign	€0.72	€4.32
Qwen 3.6 27B	Latest generation — analysis & vision, efficient	EU-sovereign	€0.48	€3.24
GLM 5.2	Agentic reasoning — tool use, code, long chains	EU-sovereign	€0.95	€3.10
Llama 3.3 70B	All-rounder — text, summarization, extraction	EU-sovereign	€0.80	€0.80
Mistral Small 3.2	Fast & cheap — triage, routine, agents	EU-sovereign	€0.11	€0.34
gpt-oss-20B	Compact reasoning — the cost sweet spot	EU-sovereign	€0.05	€0.18
Claude · GPT · Gemini	Frontier reasoning — through the same router	Routing	Provider price + fixed platform fee

Always the latest model version — upgrades automatic · metered per tenant to the second · volume tiers from 100M tokens/month

Batch: non-urgent bulk jobs via /v1/batches at ~half price — we pass the provider batch discount straight through.

Managed RAG & embeddings

Text and PDF documents in, answers out: the platform handles extraction, chunking, embeddings and the index — isolated per tenant, via /v1/rag.

Service	Unit		Price
Embeddings · Qwen3-Embedding 8B	per 1M tokens	EU-sovereign	€0.12
Embeddings · bge-m3 (multilingual)	per 1M tokens	EU-sovereign	€0.02
Vector storage	per GB / month	EU-sovereign	€0.25
RAG queries (search + context)	per 1,000 queries	EU-sovereign	€0.40

Collections, documents, files and query through one API · ingestion is billed as embedding tokens, nothing else

Create API key →

Early access: API keys right in your workspace · starter quota included

Your OpenAI client already works.

The API is OpenAI-compatible: swap the base URL, drop in a key — and your existing code talks to sovereign EU models. No new SDK, no migration.

◦ ◦ ◦ client.py

from openai import OpenAI

client = OpenAI(

base_url="https://api.linkworld.ai/v1",

api_key="rk_live_…",

)

client.chat.completions.create(

model="gpt-oss-120b", …

)

OpenAI-compatible · /v1/chat/completions

Personal data never touches a non-EU model.

Every call carries its intent: tier picks the model class, contains_pii arms the PII gate — enforced centrally, every model choice logged as evidence for EU-AI-Act audits. The default path stays EU end-to-end, with no US processor; frontier models are a deliberate, logged opt-in for tasks without personal data.

◦ ◦ ◦ policy

"tier": "eu-sovereign"

→ default: EU backend, provider-independent

"contains_pii": true

→ PII gate: forces an EU-sovereign model

"tier": "frontier" + "contains_pii": true

→ 403 policy_violation — blocked centrally, logged

Model policy · enforced centrally

Headless · Platform API

Your product. Our runtime.

You're building a SaaS product and want to ship agentic features — without running agent infrastructure yourself. Your software consumes Linkworld headless: your customers only ever see your product. Metered and billed per end customer.

One tenant per end customer

Isolated data, credentials, audit trail and usage numbers — per customer of your product.

Tools stay on your side

Agents work with your domain APIs via MCP — the business logic stays in your product.

Approval & audit included

The approval layer and audit log apply headless too — configurable per end customer.

◦ ◦ ◦ api.linkworld.ai

POST /v1/agents/{agent}/invocations

→ agent run inside your end customer’s tenant, SSE streaming

PUT /v1/tenants/{customer}/mcp-bindings/crm

→ your domain API becomes this tenant’s MCP tool

GET /v1/tenants/{customer}/usage

→ metering per end customer, billing-ready

Platform API · tenant-scoped

MCP-native

Your systems speak MCP.

The Model Context Protocol isn’t an add-on here — it’s how agents reach tools, yours and ours alike.

Domain APIs as MCP bindings

Attach your CRM or ERP per tenant as an MCP tool — agents use it like a platform tool, scope-gated.

Every app speaks MCP

Apps reach platform tools via MCP with skill gating: the agent only sees what the tenant is entitled to.

Your coding agent connects

Claude Code, Cursor & co. connect directly to the platform — lint, deploy and test console as MCP tools.

The architecture

One runtime. Every layer.

From UI to isolated execution: your apps and products sit on top — everything underneath is Linkworld.

Your apps & products

Agentic apps · your SaaS via API · AI chat

Agent teams & workflows

Orchestration, states, approvals

Tools & integrations

APIs, databases, SaaS, MCP

Memory & knowledge

Short- and long-term context, RAG

Multi-LLM router

Best model per task, failover, EU-sovereign by default

Guardrails & approval layer

Security gate, policies, audits

Execution & metering

Isolated runtime, scaling, usage per tenant

Agent levels

From answers to autopilot — one scale.

The same runtime carries every autonomy level. You decide per app and per tenant how far it may go.

Level 1–2Answers & uses tools

Knowledge agents and tool access — controlled, auditable.

Level 3–4Runs workflows & plans

Multi-step workflows with rules, intermediate steps and approvals.

Level 5–6Works in systems & automates

Operator agents and whole agentic apps — up to the business process.

Compliance & trust

European, transparent, verifiable.

EU hosting

Compute and storage exclusively in EU data centers. Sub-processors documented.

GDPR-native

DPA available, data-subject rights as product features — no compliance theater.

EU-AI-Act-ready

Risk classes, transparency logs and human oversight built in.

Audit trail

Every action logged in a structured way, retention per tenant, export for audits.

Start right now.

No framework agreement, no sales cycle: create a workspace, grab an API key, first request in minutes. As your volume grows, the tiers grow with you.

Start free Build apps →

EU-sovereign AI infrastructure.Multi-LLM, metered per tenant.