AI & LLM tools·Cost Tools

AI API Cost Calculator

Calculate AI API usage cost for GPT-5, Claude 4, Gemini 3, and Llama 4 by tokens per request, daily volume, and yearly budget.

Added May 3, 2026 · Updated May 26, 2026

Input

Model

Input tokens per request

Output tokens per request

Requests per day

Result

Enter a value for model to see your result.

How it works

Calculate daily, monthly, and yearly AI API costs for any model and request volume. Compare GPT-5, Claude 4, Gemini 3, and Llama 4 options for your workload.

Step by step

01Select the AI model you plan to use.
02Enter the average number of input tokens per request (your prompt length).
03Enter the average number of output tokens per request (expected response length).
04Enter how many requests you expect per day.
05The calculator shows cost per request, per day, per month, and per year.

Examples

Chatbot at 1,000 requests/day on GPT-5.4 mini

A typical chatbot with short prompts and responses costs about $52 per month on GPT-5.4 mini at 1,000 req/day.

Inputs

Model:: gpt-5-4-mini
Input tokens per request:: 500
Output tokens per request:: 300
Requests per day:: 1000

Result

Cost per day:: $1.73
Cost per 30 days:: $51.75

Note: Pricing figures are informational and based on publicly published rates as of 2026-05. Always verify at the provider's pricing page. Context caching discounts (available on some models) are not included. Real costs may be lower for repeated context. Llama 4 Maverick is open-weights; cost depends on your hosting provider or self-hosting infrastructure.

Frequently asked questions

How is AI API cost calculated?

You pay separately for input tokens (your prompt) and output tokens (the model's response). Cost = (input_tokens / 1,000,000) × input_price + (output_tokens / 1,000,000) × output_price. Multiply by daily requests for ongoing costs.

Which model is cheapest for high-volume workloads?

Among current-generation listed models, GPT-5.4 mini and Claude Haiku 4.5 are lower-cost hosted options, while Llama 4 Maverick varies by provider or self-hosting setup. At high volume, model choice can change monthly spend by 5–20×.

What counts as an input token vs output token?

Input tokens include your system prompt, conversation history, and the user's message. Output tokens are everything the model generates in its response. Long system prompts and history are often the biggest cost drivers.