Avatar
Margarita Tyumenkova

Hello Oyvineng ,

A similar request is reported in https://youtrack.jetbrains.com/issue/LLM-15057.

Please vote for it to prioritize it for the development team and receive notifications from the ticket. 

1

I would like to  use https://x.ai/news/grok-code-fast-1 as my AI assistant as well.  The cost per token is much better than the average, especailly Claude.

x.ai pricing is as follows.

  • $0.20 per million input tokens
  • $1.50 per million output tokens
  • $0.02 per million cached input tokens
0

Hi Mzlittle - see if it helps to apply the workaround mentioned in the description of LLM-15057 (namely, use OpenAI API+LiteLLM)

0

请先登录再写评论。