Estimate LLM API costs for your team
Estimate your team's usage
Which kind of model do you prefer?
Cost Estimation
Recommended model
gpt-4oCost per member
$0.00 /month
Total cost
$0.00 /month
Cost estimation for all models* Based on the information you've provided above
| Model | Context | |||||
|---|---|---|---|---|---|---|
| OpenAI |  o1-mini | 128k | $0.003 | $0.0015 | $0.00 /mo | $0.00 /mo |
| OpenAI | o1-preview | 128k | $0.015 | $0.012 | $0.00 /mo | $0.00 /mo |
| OpenAI | chatgpt-4o-latest | 128k | $0.005 | $0.015 | $0.00 /mo | $0.00 /mo |
| OpenAI | gpt-4o | 128k | $0.0025 | $0.01 | $0.00 /mo | $0.00 /mo |
| OpenAI | gpt-4o-miniNew | 128k | $0.00015 | $0.0006 | $0.00 /mo | $0.00 /mo |
| OpenAI | gpt-4 | 8,192 | $0.03 | $0.06 | $0.00 /mo | $0.00 /mo |
| OpenAI | gpt-4-turbo | 128k | $0.01 | $0.03 | $0.00 /mo | $0.00 /mo |
| OpenAI |  gpt-3.5-turbo | 16k | $0.003 | $0.006 | $0.00 /mo | $0.00 /mo |
| Mistral AI |  mistral-large-latest | 128k | $0.002 | $0.006 | $0.00 /mo | $0.00 /mo |
| Mistral AI | pixtral-large-latest | 128k | $0.002 | $0.006 | $0.00 /mo | $0.00 /mo |
| Mistral AI | mistral-small-latest | 32k | $0.0002 | $0.0006 | $0.00 /mo | $0.00 /mo |
 gemini-1.5-flash | 1M | $0.000075 | $0.0003 | $0.00 /mo | $0.00 /mo | |
| gemini-1.5-flash-8b | 1M | $0.0000375 | $0.00015 | $0.00 /mo | $0.00 /mo | |
| gemini-1.5-pro | 2M | $0.00125 | $0.005 | $0.00 /mo | $0.00 /mo | |
| gemini-pro | 32k | $0.0005 | $0.0015 | $0.00 /mo | $0.00 /mo | |
| Anthropic |  claude-3.5-sonnet | 200k | $0.003 | $0.015 | $0.00 /mo | $0.00 /mo |
| Anthropic | claude-3.5-haiku | 200k | $0.001 | $0.005 | $0.00 /mo | $0.00 /mo |
| Anthropic | claude-3-opus | 200k | $0.015 | $0.075 | $0.00 /mo | $0.00 /mo |
| Anthropic | claude-3-sonnet | 200k | $0.003 | $0.015 | $0.00 /mo | $0.00 /mo |
| Anthropic | claude-3-haiku | 200k | $0.0025 | $0.00125 | $0.00 /mo | $0.00 /mo |
Need more detailed calculations for each model?Click on the model to get more details
- OpenAI o1-mini
- OpenAI o1-preview
- OpenAI chatgpt-4o-latest
- OpenAI gpt-4o
- OpenAI gpt-4o-mini
- OpenAI gpt-4
- OpenAI gpt-4-turbo
- OpenAI gpt-3.5-turbo
- Anthropic claude-3.5-sonnet
- Anthropic claude-3.5-haiku
- Anthropic claude-3-opus
- Anthropic claude-3-sonnet
- Anthropic claude-3-haiku
- Google gemini-1.5-flash
- Google gemini-1.5-flash-8b
- Google gemini-1.5-pro
- Google gemini-pro
- Mistral AI mistral-large-latest
- Mistral AI pixtral-large-latest
- Mistral AI mistral-small-latest
Frequently Asked Questions
What is a token?
A token is a part of a text that can be a word, subword, punctuation mark, or symbol. If you need a programmatic interface for tokenizing text, check out the Tiktoken package for Python. For JavaScript, the community-supported @dbdq/tiktoken package works with most GPT models.
What size of image is used in this calculation?
We default the dimension of the image to 1000x1000px, which is roughly 765 to 1334 tokens based on different models.
What size of PDF is used in this calculation?
We set the default size of the PDF file to around 6,000 tokens (4,500 words), which is roughly 5 pages of full text in the PDF file.
What is the definition of 'conversations' in this calculation?
Conversations include both your questions and the AI's responses, and may contain multiple of your follow-ups (you ask follow-up questions, then the AI responds).
How accurate is the usage estimation?
The estimation tool provides an approximate usage based on the information you input. It is intended to give a general idea of your usage patterns and potential costs.
Can I change the frequency and type of interactions in the usage estimator?
Yes, the estimator allows you to set the frequency (e.g., daily, weekly) and type of interactions (e.g., Short, Medium, Long, Very Long) to better match your team's usage patterns.
What model types can I choose in the estimator?
The estimator offers four model types: Smartest, Cheapest, Fastest, and Specify. Choose the one that best suits your team's needs based on performance and cost considerations.
How often should I update the usage estimates?
You should update the usage estimates whenever there are significant changes in your team's size, interaction frequency, or file upload patterns to ensure accuracy.
How does the app handle different file types in the estimation?
The estimator allows you to input the number of images and PDFs uploaded by each member and the frequency of these uploads. This helps in providing a comprehensive usage estimate.
Bring AI to your team today!
