Apertus-v1.5-70B
Apertus v1.5 70B is the large model of the Swiss AI Initiative's open-source Apertus 1.5 family, pretrained on 17 trillion tokens and multimodal: it accepts images, audio and text and generates text, with an optional thinking mode that improves reasoning performance.
text + image + audio → text · made by swiss-ai
$0.82→$2.92per Mtok in / out
Hugging Face Inference Providers
Sold by 1 way
| Seller | Lane | Rate |
|---|---|---|
| Hugging Face Inference Providers aggregator | publicai | $0.82per Mtok in$2.92per Mtok outrouter.huggingface.co · read 2026-08-25 |
About
Apertus-v1.5-70B — a text model from swiss-ai.
It takes text, images and audio and returns text, with a context window of 262,144 tokens. It was published in July 2026. Its sellers say it can call a tool. The catalogue files it under chat.
Every current figure
- Maker
- swiss-ai
- Register
- model
- Takes
- text + image + audio
- Returns
- text
- Context
- 262,144 tokens
- Longest answer
- 8,192 tokens
- Published
- July 2026
- Parameters
- 70 billion · read from its own name
- Licence
- not read
Known as 1 name
swiss-ai/Apertus-v1.5-70B