AI Cost Calculator
Compare token costs across OpenAI, Anthropic, and Google AI models. Calculate your estimated monthly API spending based on usage.
Monthly Cost Comparison
| Model | Provider | Input $/1M | Output $/1M | Monthly Cost |
|---|---|---|---|---|
Gemini FlashCheapest | $0.07 | $0.30 | $0.675 | |
Claude Haiku | Anthropic | $0.25 | $1.25 | $2.63 |
GPT-3.5 Turbo | OpenAI | $0.50 | $1.50 | $3.75 |
Gemini Pro | $1.25 | $5.00 | $11.25 | |
GPT-4o | OpenAI | $2.50 | $10.00 | $22.50 |
Claude Sonnet | Anthropic | $3.00 | $15.00 | $31.50 |
Claude Opus | Anthropic | $15.00 | $75.00 | $157.50 |
GPT-4 | OpenAI | $30.00 | $60.00 | $180.00 |
How to Use
- Enter the number of input tokens per request (prompt tokens sent to the model).
- Enter the number of output tokens per request (tokens the model generates).
- Set the number of API requests you make per day.
- Adjust the number of days per month your application runs.
- View the cost comparison chart and table to find the most cost-effective model for your use case.
Frequently Asked Questions
How are AI API costs calculated?
AI APIs charge per token processed. Tokens are pieces of text — roughly 4 characters or 0.75 words in English. Each model has separate pricing for input tokens (your prompt) and output tokens (the model's response). Monthly cost = (tokens per request × requests per day × days per month × price per token).
Which AI model is the cheapest?
As of April 2026, Google's Gemini Flash is the most affordable option at $0.075/1M input tokens and $0.30/1M output tokens. Claude Haiku and GPT-3.5 Turbo are also very cost-effective options for simpler tasks.
What's the difference between input and output tokens?
Input tokens are the tokens in your prompt — the text you send to the AI model. Output tokens are the tokens the model generates in its response. Output tokens are typically more expensive than input tokens because they require more computation.
How many tokens does a typical request use?
A short query might use 100-500 input tokens and 200-1000 output tokens. A longer conversation with context could use 2,000-8,000 input tokens. Code generation tasks often produce 500-3,000 output tokens. The exact count depends on your specific use case.
Are these prices up to date?
These prices reflect approximate API pricing as of April 2026. AI providers occasionally adjust their pricing, so check the official pricing pages for the most current rates.