Inference that stays in the EU, billed per call

If the text your agent sends is customer data, a US inference provider is a problem your legal department will find later. An EU region on a US provider does not solve it either, because the parent company remains subject to US law.

This lane runs on infrastructure in Germany. Inputs are not used for training and prompts are not logged; we store token counts, never content. The API is OpenAI-compatible and supports tool use, so an existing client works with a changed base URL.

Pricing is by weighted tokens, quoted in the 402 before the call runs, so an agent knows the price of a request before it spends anything.

Endpoints (3)

Method	Path	What you get	USDC
`POST`	`/ai/v1/eu-chat`	GDPR-compliant LLM chat completion hosted in Germany (EU data residency, no training on inputs, no prompt logging), OpenAI-compatible with tool use (paid)	0.01
`POST`	`/ai/v1/eu-embed`	GDPR-compliant text embeddings, processed exclusively in Germany (paid)	0.01
`GET`	`/ai/v1/eu-llm-info`	Models, limits and GDPR guarantees of the EU inference lane (free)	free

Calling it

An unpaid request answers HTTP 402 with the price and the payment details. Pay that amount in USDC on Base, then repeat the same request with the payment header — any x402 client does this for you.

curl -i -X POST https://agent.connskill.com/ai/v1/eu-chat \
  -H 'Content-Type: application/json' \
  -d '{"messages":[{"role":"user","content":"Summarise this in one sentence: ..."}],"max_tokens":256}'

One free sample per endpoint per day: add the header x-free-sample: 1 on any endpoint priced 0.15 USDC or less.

Through MCP

claude mcp add --transport http connskill https://agent.connskill.com/mcp

npx -y @connskill/mcp-growth-services   # local, pays for you with X402_WALLET_KEY

The rest of the catalogue

SEO data · Numbers & inboxes · Trust & exposure · Website analytics · Social marketing

Full price table: /pricing · machine-readable: /openapi.json, /.well-known/x402, /llms.txt