Opper AI partners with Regolo to bring green inference with zero data retention to the gateway

Stockholm, Sweden, August 2026. Opper AI and Regolo are partnering to bring Regolo's green-compute inference to the Opper AI gateway, served from Seeweb's own datacenters in Europe on renewable energy. Builders can now reach twelve Regolo-hosted models through the Opper API, from GLM-5.2 and GPT-OSS 120B to Qwen3 Coder Next, Llama 3.3 70B, the fully open Apertus 70B, and Regolo's own Brick Complexity Pro, with zero data retention on by default.

Why this matters

Genuinely green inference. Regolo serves its models from Seeweb's own European datacenters, run entirely on renewable energy, cooled without water, and ISO 14001 certified. The footprint of a call is a property of the infrastructure itself, which makes Regolo a natural route for teams with sustainability commitments of their own.

A European route under EU law. Regolo is the AI platform of Seeweb S.r.l., a European cloud provider in the DHH group, so inference runs in Europe and processing stays under EU law. The DPA is published as part of the terms, there is no training on customer data, and zero data retention is the platform default, with prompts and outputs handled in volatile memory and never written to disk. The full privacy detail lives on the Regolo provider page.

Open-weight staples, plus two firsts. The catalogue covers the models teams actually run, GLM-5.2, GPT-OSS, the Qwen 3.5 and 3.6 families, Qwen3 Coder Next, Llama 3.3 70B, Gemma 4 31B, and Mistral Small 4, and brings two firsts to the directory: the Swiss AI Initiative's Apertus 70B, open in the strictest sense with weights, training data, and recipes all published, and Regolo's own Brick Complexity Pro, a lightweight classifier that scores prompt difficulty so routing pipelines can pick a model tier before spending tokens on generation.

More than a router: the AI control plane. Routing to Regolo is just the entry point. Every call through Opper runs on its AI control plane: intelligent routing across models and regions, full observability, real-time PII masking and content filtering, budget caps, and audit trails. Pin Regolo for a task or set it as a fallback, and because Regolo is OpenAI-compatible, getting there is a model string, not a migration.

"We're glad to welcome Regolo to Opper. Open models served from their own European datacenters, on renewable energy and with zero data retention by default, is a combination our developers can put to work immediately."

— Göran Sandahl, Co-founder and CEO, Opper AI

"We built Regolo so teams can run AI on infrastructure that is green by design and compliant under EU law, in our own datacenters powered by renewable energy. Opper brings that to a wide community of builders through one API, and we look forward to what they ship with it."

— Antonio Baldassarra, CEO, Seeweb

Models live today

The catalog below is fetched live from Opper's model API and filtered to Regolo-hosted models. Availability, context windows, and pricing stay in sync with what's actually callable through Opper. All Regolo routes are hosted in Europe.

Get started

Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up Opper and route to Regolo for you:

Use curl to download, read and follow: https://skills.opper.ai
Then set up Opper to use Regolo as the provider, e.g. regolo/gpt-oss-120b.

Prefer a direct call? Opper is drop-in compatible with the OpenAI, Anthropic, and Google SDKs, so one API key and the model string are all you need:

OpenAIAnthropicGeminicURL

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "regolo/gpt-oss-120b",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);

Follow the quick start in our docs for evaluations, fallbacks, and structured output.

About Regolo

Regolo is the AI inference platform of Seeweb S.r.l., a European cloud provider in the DHH group, serving open-weight models through an OpenAI-compatible API from Seeweb's own European datacenters, powered entirely by renewable energy and ISO 14001 certified. Zero data retention is the platform default and there is no training on customer data.

About Opper AI

Opper AI is the European AI gateway and control plane for agents: one EU-hosted, GDPR-compliant API across 700+ models, with smart routing, automatic fallbacks, built-in evaluations and observability, real-time guardrails, and full OpenAI SDK compatibility.