Deepseek V3 and R1 are supported in 0.45 and 0.44!
You can enable them in Settings > Models > turning on deepseek-r1
or deepseek-v3
. We host these models in the US.
Deepseek V3 and R1 are supported in 0.45 and 0.44!
You can enable them in Settings > Models > turning on deepseek-r1
or deepseek-v3
. We host these models in the US.
But when will it support the composer?
Yes when does that happen?
Will they be considered premium models or not?
I noticed that it’s super fast, how many billion parameters does it use?
Those answers have been already supplied several times in the forum. It uses the full model, its premium but doesnt count as fast request AFAIK.
How much parameters these models?
For anyone else who refuses to use the search button, its 671B parameters.
Any idea why it doesn’t seem as good as the version you get on the deepseek website?
See
Is the explanation here most likely correct?
Is there a way to add Deepseek with my own API key? We’re running it in Azure and would like to use it instead of Deepseek API.
Cursor does not use the Deepseek API. They use Fireworks for hosting Deepseek.