---
last_updated: 2026-11-20
source_url: https://opper.ai/swiss-ai/apertus-70b
title: "Apertus 70B by Swiss AI Initiative"
description: "Apertus 70B, the Swiss AI Initiative's fully open model from EPFL and ETH Zurich, trained on 15T tokens with over 1,800 natively supported languages."
---

# Apertus 70B

By [Swiss AI Initiative](https://opper.ai/swiss-ai).

Released 2 Sep 2025 · [Announcement](https://ethz.ch/en/news-and-events/eth-news/news/2025/09/press-release-apertus-a-fully-open-transparent-multilingual-language-model.html) · [All Swiss AI Initiative releases](https://opper.ai/model-releases/swiss-ai)

Apertus 70B is the fully open flagship of the Swiss AI Initiative, a collaboration between EPFL, ETH Zurich, and CSCS that trained the model on the Alps supercomputer in Lugano and released it in September 2025. The 70 billion parameter decoder-only transformer was pretrained on 15 trillion tokens, and the project publishes far more than weights, including the training data, recipes, code, and intermediate checkpoints. Training used the Goldfish loss, an objective that intentionally limits verbatim memorization of the corpus.

Multilingual reach is the standout, with more than 1,800 natively supported languages and deliberate weight on underrepresented ones, alongside tool calling and structured output over a 64K context window. It fits teams that want a capable general model whose entire pipeline can be audited, from research and public-sector deployments to multilingual products that go beyond the usual high-resource languages.

## Available routes

Apertus 70B runs on 1 route through the Opper gateway. Prices are per 1M tokens. In the EU it is served by Regolo (Italy). [See every model hosted in the EU](https://opper.ai/models/eu). Its routes and prices, live from the catalogue, are public JSON with no API key needed at https://api.opper.ai/v3/models?q=regolo%2Fapertus-70b.

| Provider | Model id | Region | Zero data retention | Training | Input | Output | Cache read |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Regolo](https://opper.ai/provider/regolo) | `regolo/apertus-70b` | EU (Italy) | Yes | No | $0.44 | $2.31 | Input price |

## Key info

- Model id: `regolo/apertus-70b`
- Input: Text
- Output: Text
- Features: Tools, Structured output
- Context window: 66K
- Max output: n/a
- Input price: $0.44 per 1M tokens
- Output price: $2.31 per 1M tokens
- Released: 2 Sep 2025
- EU residency available
- Zero data retention on pay-as-you-go
- No training by default

## Data handling per route

Each route hosting Apertus 70B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

### Regolo — Italy

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. EU.

- Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: No classifier
- Subprocessor access: No subprocessor reads content
- Transfer mechanism: Not applicable — data stays in EU

Verified by Opper on 2026-07-30.

## Benchmarks

Independent benchmark scores via [Artificial Analysis](https://artificialanalysis.ai) ([view on AA](https://artificialanalysis.ai/models/apertus-70b-instruct)). Indices and domain scores are out of 100, Omniscience runs from −100 to 100, Briefcase is an Elo rating, and the other evaluation scores are the share of tasks solved.

- Global rank: #494 of 520 LLMs on the [LLM leaderboard](https://opper.ai/llm-leaderboard)
- Tier: Efficient
- Intelligence Index (previous version): 5.1

### Agentic & knowledge work

- Terminal-Bench Hard: 0%
- τ²-Bench Telecom: 13%

### Science & reasoning

- Humanity's Last Exam: 6%
- GPQA Diamond: 27%
- Long-context reasoning: 0%

### Math & instruction following

- IFBench: 26%

## Get started

Call Apertus 70B through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Apertus 70B is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

### Set it up with your agent

Paste this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper for you:

```text
Use curl to download, read and follow: https://skills.opper.ai Call Apertus 70B
```

### Or call it directly

OpenAI:

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const completion = await client.chat.completions.create({
  model: "regolo/apertus-70b",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);
```

Anthropic:

```javascript
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const message = await client.messages.create({
  model: "regolo/apertus-70b",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(message.content);
```

Gemini:

```javascript
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: process.env.OPPER_API_KEY,
  httpOptions: { baseUrl: "https://api.opper.ai/v3/compat" },
});

const response = await ai.models.generateContent({
  model: "regolo/apertus-70b",
  contents: "Hello",
});
console.log(response.text);
```

cURL:

```bash
curl https://api.opper.ai/v3/compat/chat/completions \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "regolo/apertus-70b",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'
```

## Use Apertus 70B in your apps

Pick your tool to see how to run it on Apertus 70B through Opper.

- [Claude Code](https://opper.ai/apps/claude-code/apertus-70b)
- [Claude Cowork](https://opper.ai/apps/claude-cowork/apertus-70b)
- [Codex](https://opper.ai/apps/codex/apertus-70b)
- [DeepSeek Harness](https://opper.ai/apps/deepseek-harness/apertus-70b)
- [GitHub Copilot CLI](https://opper.ai/apps/github-copilot-cli/apertus-70b)
- [Aider](https://opper.ai/apps/aider/apertus-70b)
- [Goose](https://opper.ai/apps/goose/apertus-70b)
- [Droid](https://opper.ai/apps/droid/apertus-70b)
- [OpenCode](https://opper.ai/apps/opencode/apertus-70b)
- [Pi](https://opper.ai/apps/pi/apertus-70b)
- [OpenClaw](https://opper.ai/apps/openclaw/apertus-70b)
- [Hermes](https://opper.ai/apps/hermes/apertus-70b)
- [Copilot for Obsidian](https://opper.ai/apps/obsidian-copilot/apertus-70b)
- [OmniRoute](https://opper.ai/apps/omniroute/apertus-70b)
- [Cursor](https://opper.ai/apps/cursor/apertus-70b)
- [Cline](https://opper.ai/apps/cline/apertus-70b)
- [Continue](https://opper.ai/apps/continue/apertus-70b)
- [Kilo Code](https://opper.ai/apps/kilo-code/apertus-70b)
- [GitHub Copilot](https://opper.ai/apps/github-copilot/apertus-70b)
- [Zed](https://opper.ai/apps/zed/apertus-70b)
- [JetBrains AI Assistant](https://opper.ai/apps/jetbrains-ai-assistant/apertus-70b)
- [Voidleap Code](https://opper.ai/apps/voidleap-code/apertus-70b)
- [n8n](https://opper.ai/apps/n8n/apertus-70b)
- [LibreChat](https://opper.ai/apps/librechat/apertus-70b)
- [Open WebUI](https://opper.ai/apps/open-webui/apertus-70b)
- [See all apps](https://opper.ai/apps)
