Welcome to the LLM (Large Language Model) services provided by ScaDS.AI. Our API offers flexibility and efficiency, enabling you to seamlessly integrate sophisticated LLMs into your applications.
For an overview, check out our poster.
The easiest way to use our LLMs is the ScaDS.AI Chatbot on Slack (ScaDS.AI employees only). Alternatively, you might try our Chat Web Interface, where you can log in with your university account and start chatting in multiple languages.
Our services are compatible with the OpenAI API and can even be integrated into your text editor or IDE.
Please see our repository
of usage examples for further information what is possible.
To access our services, you need an API key. To get one, please send an email to scadscat@tu-dresden.de
with the following information:
⚠ Please don't share the API key with other people.
We retain the right to change models, so that we can provide models that suits your applications and our infrastructure best. You can, however, use one of the following model aliases for more reliable applications:
⚠ Behind each alias, there is a default model and a chain of fallback models that are tried if the default model is unhealthy.
The exact model that provided the output is mentioned in the response. If you want to avoid using fallbacks, use "disable_fallbacks": true
as described on the LiteLLM documentation. If you use the openai Python library, add parameter extra_body={"disable_fallbacks": true}
to the client.chat.completions.create
call.
Please review the usage policies and rules of this service before using it. By using the service, you agree to comply with these policies and rules.
Please contact scadscat@tu-dresden.de