Your model, your credentials
EDN never supplies a model. In the Workspace, you connect the provider and model
you want to use through the settings opened from the chat status row.
Providers
The settings support these providers:
- Anthropic, using an Anthropic API key.
- OpenAI, using an OpenAI API key.
- NVIDIA NIM, using an NVIDIA API key. The NVIDIA NIM free tier is available
from build.nvidia.com at 40 requests per minute.
- Local or self-hosted, using an inference endpoint URL and an optional API key.
You then choose a model from the list of models available for the connected
provider.
Inference settings
You can set the temperature, the maximum number of tokens, and an optional seed
for the response.
Your provider key lives only in the settings for that session. It is not
saved to your browser or persisted by the Console.
