NVIDIA Llama 3.3 Nemotron Super 49B v1 Cost Calculator

This calculator helps you estimate the cost of using the NVIDIA Llama 3.3 Nemotron Super 49B v1 model. Input your token usage and the number of requests to get an approximate cost.

The pricing is as follows:

• Input Tokens: $0.13 per 1 Million tokens
• Output Tokens: $0.4 per 1 Million tokens

The model boasts a substantial context window of 131072 tokens, allowing for processing of large amounts of information.

Formula:
Cost = (Number of Input Tokens / 1,000,000) * Input Cost per 1M Tokens * Number of Requests + (Number of Output Tokens / 1,000,000) * Output Cost per 1M Tokens * Number of Requests

Example:
If you use 50,000 input tokens and 10,000 output tokens for 2 requests:
Input Cost = (50,000 / 1,000,000) * $0.13 * 2 = $0.013
Output Cost = (10,000 / 1,000,000) * $0.4 * 2 = $0.008
Total Cost = $0.013 + $0.008 = $0.021

Note: Calculation is approximate based on public data. Prices may change, check official websites.