I truly love your channel. Keep doing the best work. 😊
@HimanshuSingh-j6bАй бұрын
Thank you so much 😀
@harsh-sharma-15Ай бұрын
hi himanshu i have one doubt how llama 3.3 costing has 0.1$ for 1m tokken . do we need to api to call it's that price or we download the model to local and we infrence it to 1m token then the total cost of hardware consuption and electricty. its that price i am confused
@justl449428 күн бұрын
its the total tokens, prompt + response. and the cost is only on api