<!-- TITLE: LLMduckt -->
<!-- DESCRIPTION: Teaching staff use the TeachCenter to give students a key of their own for AI language models — for programming against the interface. -->
<!-- LANG: en -->
<!-- URL: https://flaait.tugraz.at/en/services/llmduckt/ -->
<!-- URL_DE: https://flaait.tugraz.at/services/llmduckt/ -->
<!-- URL_EN: https://flaait.tugraz.at/en/services/llmduckt/ -->
<!-- TYPE: service -->
<!-- STATUS: pilot -->
<!-- PILLARS: ai, future -->
<!-- PILLAR_TITLES: AI for Teaching, Future Learning -->
<!-- DETAIL: full -->

# LLMduckt

*Teaching staff use the TeachCenter to give students a key of their own for AI language models — for programming against the interface.*

**Key facts**

- **Focus areas:** AI for Teaching, Future Learning
- **Status:** Pilot
- **Address:** [llm.tugraz.at](https://llm.tugraz.at)
- **Interface:** OpenAI-compatible API
- **Access:** API key via the TeachCenter course
- **Operated by:** Educational Technology unit (OE Lehr- und Lerntechnologien)
- **Contact:** [telucation@tugraz.at](mailto:telucation@tugraz.at)

Teaching with AI language models calls for more than chat windows: it also calls for access to the programming interface — and for that, a key of their own for every student. LLMduckt provides both: teaching staff choose the models, the TeachCenter hands the API keys out to the course.

In programming courses, the interface itself is the subject matter: students write code that calls a language model. For that, LLMduckt gives each of them a key of their own for an application programming interface (API) compatible with the OpenAI API — so existing libraries and code examples keep working. For working in the browser there is *Academic AI*, the chat service for TU Graz staff; the two complement each other.

Teaching staff decide which models their course may use — and with that, where the computation happens. The choice includes models on TU Graz servers as well as models at external providers; the current list is published under [available models](https://llm.tugraz.at/models-available).

## Setting it up for a course

TeachCenter support does the activation; for teaching staff it comes down to three steps:

- From the [available models](https://llm.tugraz.at/models-available), pick the ones the students should use.
- Contact [TeachCenter](https://tc.tugraz.at) support, naming the course and the chosen models.
- Once activated, a link appears in the course through which students retrieve their key and sample code.

Credentials and API keys are confidential: they must not be passed on or published — not even inadvertently in a public repository. The details are set out in the [terms of use](https://llm.tugraz.at/benutzerrichtlinie).

> **News**
> **Service launch in autumn 2026**
>
> LLMduckt is available as a service of the Educational Technology unit from autumn 2026. From then on, teaching staff can have their courses activated through [TeachCenter](https://tc.tugraz.at) support.

## Further links

- [Open LLMduckt · llm.tugraz.at](https://llm.tugraz.at)
- [Frequently asked questions (FAQ) · Setup, difference from Academic AI, access](https://llm.tugraz.at/faq)
- [Available models · llm.tugraz.at/models-available](https://llm.tugraz.at/models-available) (TU Graz account)
- [TeachCenter of TU Graz · Course administration and key distribution](https://tc.tugraz.at) (TU Graz account)

- [Imprint](https://tugraz.at/go/impressum)
- [Terms of use](https://llm.tugraz.at/benutzerrichtlinie)
- [FAQ](https://llm.tugraz.at/faq)