Grokking the Solutions Architect Interview
0% completed
Choosing Models and Controlling Cost
The retailer's customer service assistant pays for its large language model (LLM) by the token: input tokens go to the model, and output tokens come from it.
This lesson keeps the earlier assumption of 200,000 conversations a month, each with 2 requests: 6,000 input tokens and 600 output tokens per conversation. The prices below are illustrative, per million tokens, and are not any provider's current price list.
| Model | Input price | Output price | Input cost | Output cost | Monthly total |
|---|
.....
.....
.....
Like the course? Get enrolled and start learning!
Reading Progress
0%