Typing Mind

Featherless can power your sessions in Typing Mind and this article shows you how to reconfigure your install.

TypingMind

Choose OpenAI compatible API in the API type.
Enter Endpoint https://api.featherless.ai/v1/chat/completions
Choose a Model from https://featherless.ai/models and copy its model ID.
The context length depends on the model’s class. Using 4096 as a starters. You can find the max model’s context length from the class in the model type section here
You will add a custom headers with it’s key authorization and the key will be Bearer <Your-API-Key-Here>
Then add a custom body params as a number the key will be max_tokens and the amount can be anywhere up to 4096. This will be the length of your responses