Model: DeepSeek: DeepSeek V3.1 Base, Context: 163840, Cost: $0.2 per 1M input tokens, $0.8 per 1M output tokens
Note: Calculation is approximate based on public data. Prices may change, check official websites.
Use the DeepSeek: DeepSeek V3.1 Base API Cost Calculator to estimate your expenses when working with the powerful DeepSeek V3.1 Base model. This calculator helps you determine the cost based on the number of input and output tokens and the number of requests.
The DeepSeek V3.1 Base is a large 671B parameter Mixture-of-Experts (MoE) language model, known for its raw next-token prediction capabilities. It features a substantial context window of 163840 tokens.
The pricing structure for DeepSeek V3.1 Base is as follows:
- Input tokens: $0.2 per 1 million tokens
- Output tokens: $0.8 per 1 million tokens
The calculation is performed using the following formula:
Total Cost = ((Input Tokens / 1,000,000) × $0.2 + (Output Tokens / 1,000,000) × $0.8) × Number of Requests
For example, if you process 1,000,000 input tokens and 500,000 output tokens in a single request:
Input Cost: (1,000,000 / 1,000,000) × $0.2 = $0.2
Output Cost: (500,000 / 1,000,000) × $0.8 = $0.4
Total Cost: $0.2 + $0.4 = $0.6