Last Updated: March 13, 2024
New models: We’ve added gpt-3.5-turbo-0125, the model improves accuracy and fixes a bug for non-English texts, allowing up to 4,096 tokens.
Pricing update: OpenAI has switched their pricing unit from per 1,000 tokens to per 1,000,000 tokens.
GPTs API model pricing
Pricing is based on the total number of tokens used (input + output). Each model has its own rate per 1,000,000 tokens.
| Model | Input price | Output price |
|---|---|---|
| gpt-4-0125-preview | $10.00 | $30.00 |
| gpt-4-1106-preview | $10.00 | $30.00 |
| gpt-4-1106-vision-preview | $10.00 | $30.00 |
| gpt-4 | $30.00 | $60.00 |
| gpt-4-32k | $60.00 | $120.00 |
| gpt-3.5-turbo | $3.00 | $6.00 |
| gpt-3.5-turbo-0125 | $0.50 | $1.50 |
| gpt-3.5-turbo-1106 | $1.00 | $2.00 |
| gpt-3.5-turbo-0613 | $1.50 | $2.00 |
| gpt-3.5-turbo-16k-0613 | $3.00 | $4.00 |
| gpt-3.5-turbo-0301 | $1.50 | $2.00 |
| gpt-3.5-turbo-instruct | $1.50 | $2.00 |
What are OpenAI API models?
OpenAI API models are powerful tools that can understand, generate, and respond to human language. They can be used for various tasks, including:
- Text generation
- Code completion
- Translation
- And more!
How to use the calculator
To calculate the API costs, you can follow these steps:
1. Look at Select an OpenAI model dropdown menu to choose an API model.
2. Look at the Input tokens and Output tokens, enter the number tokens.
3. Click Calculate Price to see the estimated cost.
For example, we selected gpt-4-0125-preview with 12,345 input tokens and expect a 67,890 token response. The calculator estimates a cost of $2,16 with 60,177 words.
That’s all! The calculator will display the estimated price for the selected GPT model based on your tokens.
Learn more about the pricing calculator for the OpenAI API here.
FAQs
1. What are tokens?
Tokens are the basic unit used for billing in OpenAI’s API. Each word, punctuation mark, and special character typically counts as one token. The cost is calculated based on the total number of tokens processed, including both the input you provide (prompt) and the output generated by the AI model.
2. How to choose the right model?
Consider these factors when selecting a model:
- Task complexity: Simpler tasks can be handled by GPT-3.5 Turbo models, while complex ones might require GPT-4.
- Desired output length: Models like GPT-4 generate more content per token, making them efficient for longer responses.
Tip
Learn more about OpenAI’s model specifications for information.