# Apertus 70B Usage, Cost & Rank | OpenCode Data

> Apertus 70B costs $1.39 per 1M input tokens and $2.23 per 1M output tokens.

Fully open 70B multilingual LLM supporting 1800+ languages with 65K context. Trained on 15T tokens of compliant open data. Apache 2.0, EU AI Act compliant.

- Page: https://opencode.ai/data/swiss-ai/apertus-70b
- JSON: https://opencode.ai/data/swiss-ai/apertus-70b.json
- Model ID: swiss-ai/apertus-70b
- Lab: Swiss AI

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 66K |
| Max output | 8.2K |
| Knowledge cutoff | 2025-09 |
| Release date | 2025-09-02 |
| Input modalities | text |
| Output modalities | text |
| Reasoning | No |
| Tool calling | Yes |
| Open weights | Yes |
| Weights | [Hugging Face](https://huggingface.co/swiss-ai/Apertus-70B-Instruct-2509) |

## Pricing: USD per 1M tokens

| Input | Output | Cached input | Cache write |
| --- | --- | --- | --- |
| $1.39 | $2.23 | - | - |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.