# Apertus 70B Instruct

> Apertus 70B Instruct is an open-weight language model from Swiss AI, released on 2 Sept 2025. It accepts text and generates text, with a 66K-token context window and up to 8K output tokens per response.

Source page: https://www.aimodel.directory/models/apertus-70b
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Swiss AI
- **Release date:** 2 Sept 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llmtr/models/publicai/apertus-70b-instruct.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llmtr/models/publicai/apertus-70b-instruct.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llmtr/models/publicai/apertus-70b-instruct.toml)
- **Context window:** 66K (65,536 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llmtr/models/publicai/apertus-70b-instruct.toml)
- **Max output:** 8K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llmtr/models/publicai/apertus-70b-instruct.toml)
- **Knowledge cutoff:** Sept 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llmtr/models/publicai/apertus-70b-instruct.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llmtr/models/publicai/apertus-70b-instruct.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llmtr/models/publicai/apertus-70b-instruct.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llmtr/models/publicai/apertus-70b-instruct.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/llmtr/models/publicai/apertus-70b-instruct.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|

## FAQ

### What is the context window of Apertus 70B Instruct?

Apertus 70B Instruct has a context window of 65,536 tokens (66K) and can generate up to 8,192 tokens in a single response, according to models.dev.

### Is Apertus 70B Instruct open source?

Apertus 70B Instruct is an open-weight model. Check the license terms before commercial use.

### When was Apertus 70B Instruct released?

Swiss AI released Apertus 70B Instruct on 2 Sept 2025, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Apertus 70B Instruct", https://www.aimodel.directory/models/apertus-70b