AI API Cost Calculator
Estimate OpenAI, Claude and Gemini API costs per request, day and month. Compare models side by side, with prompt caching and long-context prices.
- No uploads
- No limits
- No signup
| Claude Haiku 5.5 | $0.00035 | $0.35 | $10.50 |
|---|---|---|---|
| GPT-4o mini | $0.00045 | $0.45 | $13.50 |
| Gemini 3.8 FlashNew price from Jan 1, 2027 | $0.00263 | $2.63 | $78.75 |
| GPT-5.4 mini | $0.003 | $3.00 | $90.00 |
| GPT-6.1 Sol | $0.007 | $7.00 | $210.00 |
| Claude Sonnet 5.5 | $0.007 | $7.00 | $210.00 |
| Gemini 3.1 Pro Preview | $0.008 | $8.00 | $240.00 |
List prices in USD for standard API requests, without batch discounts, taxes or cache-write fees. A month is 30 days. Reasoning (thinking) tokens bill as output tokens. In text mode, numbers marked ≈ are estimates because Claude, Gemini and GPT-6 tokenizers aren't public.
Prices checked Nov 5, 2026. Always confirm on the official pricing pages: OpenAI · Anthropic · Google
- Input:
- Token count · Text
- Output:
- API cost
- Runs on:
- Your device
- Size limit:
- None
- Account:
- Not needed
How to use AI API Cost Calculator
Describe a request
Enter input and output tokens per request, or paste a typical prompt to count its tokens.
Add your volume
Set requests per day or month and, if you use prompt caching, the share of input that's cached.
Compare models
Pick models and sort the table by cost per request, day or month.
Why AI API Cost Calculator on Toolshed
No uploads
Everything runs in this browser tab. Your files never leave your device.
No limits
No file-size caps, no daily quotas. Process as much as your device can handle.
No signup
No account, no email, no watermark.
Frequently asked questions
Where do the prices come from?
From OpenAI's, Anthropic's and Google's official API pricing pages, checked on the date shown under the table. Prices change often, so confirm on the linked pages before you commit to a budget.
What is the cached input share?
With prompt caching, input the provider has already seen (like a long system prompt) is billed at a much lower cached price. Enter the percentage of each request's input you expect to be cached.
Why does the price jump for long prompts?
Some models charge more for the whole request once the prompt passes a threshold, for example 272K tokens on newer GPT models, 200K on Gemini 3.1 Pro and 100K on Claude Haiku 5.5. The table marks rows where that price applies.
Are my files uploaded anywhere?
No. AI API Cost Calculator runs entirely in your browser. Your files are processed on your device and are never sent to a server.
Is there a file size limit?
No fixed limit. The only limit is your device's memory. Very large files work best in a desktop browser.
Is AI API Cost Calculator really free?
Yes. There's no account and no watermark. A short optional ad, or a 20-second wait, unlocks each download. That's how we keep it free.