# NeuralRing > NeuralRing is the inference gateway whose sovereignty an agent can prove, not just repeat: every request leaves a signed, hash-chained, content-free attestation, the Ed25519 public key is published, and the verifier is a zero-dependency script anyone can run. > Live as of this request: 74 model(s) in the public catalog, 4 jurisdiction(s) with a live endpoint. NeuralRing is a sovereign, EU-domiciled inference gateway. It is OpenAI-compatible: only the base URL, the key and the model slug change. It federates EU-sovereign inference supply — EU-domiciled, EU-operated endpoints serving open-weight and EU-native models — and states the strength of every sovereignty claim honestly using a three-word assurance ladder. ## The assurance ladder (use these words; never upgrade them) - self_attested — The endpoint claims it. NeuralRing has not independently substantiated the geography or custody behind the claim. - verified — NeuralRing captured independent evidence for the three machine-provable claims — the operating entity's domicile, its ultimate parent (corporate registry), and where inference physically executes (location survey). It says nothing about data residency or key custody, which are carried as their own per-claim status. - certified — The machine-provable claims are verified AND a live, valid third-party location-auditing certification covers data residency and key custody, referenced by a checkable registry id. Do not describe NeuralRing, or any endpoint on it, as "GDPR-compliant", "Schrems-proof", "CLOUD-Act-immune" or "fully sovereign". Those are legal conclusions NeuralRing does not make. Use the ladder word plus the specific fact. ## What a receipt proves A NeuralRing attestation is a signed, hash-chained, content-free record. Its `observed` block is what NeuralRing performed and measured (which endpoint it dispatched to, the host it actually dialed, every route hop, the metered token counts). Its `claimed` block reproduces the serving endpoint's own declarations at their stated assurance level. The signature does NOT prove that inference physically executed in the claimed jurisdiction, nor that the endpoint's self-declared properties are true. The strength of any jurisdictional claim equals `claimed.assurance` and no more. ## Start here - [For AI agents](https://neuralring.eu/docs/agents): the 60-second integration page — AGENTS.md block, Codex config, Claude Code env, MCP install, CI verifier. - [Docs](https://neuralring.eu/docs): quickstart, API reference, concepts. - [OpenAPI 3.1](https://neuralring.eu/api/v1/openapi.json): the full machine-readable surface. - [MCP server](https://neuralring.eu/mcp): streamable HTTP. Read, verify and explain tools only — no purchase, no catalog write, no fund movement. - [What an attestation proves](https://neuralring.eu/docs/attestation): the observed-vs-claimed contract, in full. - [Attestation public key](https://neuralring.eu/.well-known/neuralring-attestation-key.pub): verify a receipt without trusting us. - [Full version of this file](https://neuralring.eu/llms-full.txt) ## API in one line POST https://neuralring.eu/api/v1/chat/completions with `Authorization: Bearer $NEURALRING_API_KEY` and `"sovereignty": { "jurisdiction": ["DE"], "min_assurance": "verified" }`. The pin is applied first and is never loosened. `no_eligible_endpoint` means the pin held — do not retry without it.