Click name to equip
Threads

Provider specific model name.

If supported by the model.

Variety. Lower = predictable.

Nucleus sampling.

Token shortlist size.

Discourage repeats by count.

Reduce verbatim echoes.

Minimum token prob vs best.

Adaptive nucleus filter.

OpenAI param.

Saved per sune.


            

          

          

          
Scripts also run. extension.html runs before index.html.

        

        

                    

        

      

    

  





  

  

    

      
Account Settings

      

        

        

          
Or you can prefix model names with or:, oai:, g:, or cf: to override.

          
Stored locally.

          
Used for auto-generating thread titles.

        

        
Access with USER.apiKeyOpenRouter.
Access with USER.apiKeyOpenAI.
Gemini/AI Studio key. Access with USER.apiKeyGoogle.
Not functional right now. Access with USER.apiKeyCloudflare.
Access with USER.githubToken.
For GCP services. Access with USER.gcpSA (returns object).