Home / Tools / AI API cost calculator

AI API cost calculator

Estimate what your app would cost to run on Claude, GPT or Gemini. Enter how big each request is and how many you expect, and compare every model side by side.

  • AI tool
  • Runs in your browser
  • Tested 19 November 2026
  • Sources
Your prompt, instructions and any documents.
The model's reply.
Add your own model or price

Model$ per 1M in / outPer requestPer month

Standard list prices in US dollars, checked . A month is 30 days. Batch processing and prompt caching can cut costs a lot, and aren't included here.

How AI API pricing works

AI providers charge per token, a chunk of text that is usually part of a word. In English, 1,000 tokens is roughly 750 words. You pay separately for:

  • Input tokens: everything you send, including your instructions, the conversation so far and any documents.
  • Output tokens: everything the model writes back. These cost several times more than input tokens.

cost = (input tokens × input price + output tokens × output price) ÷ 1,000,000

Worked example. A chatbot reply with 600 input tokens and 300 output tokens on a model priced at $2 in and $10 out costs (600 × 2 + 300 × 10) ÷ 1,000,000 = $0.0042. At 1,000 replies a day, that is about $126 a month.

Current prices

ProviderModelInput / 1MOutput / 1MNotes
AnthropicClaude Fable 5.2$8$40
AnthropicClaude Opus 5.5$4$20
AnthropicClaude Sonnet 5.5$2$10
AnthropicClaude Haiku 5.5$0.10$0.50$0.50 / $2.50 above 100k input tokens
OpenAIGPT-6.2 Astra$8$40
OpenAIGPT-6.2 Sol$2$10
OpenAIGPT-6.1 Terra$1$5
OpenAIGPT-6 Luna$0.10$0.50
GoogleGemini 3.1 Pro Preview$2$12$4 / $18 above 200k input tokens
GoogleGemini 3.5 Flash$1.50$9
GoogleGemini 3.1 Flash-Lite$0.25$1.50

Prices change often, so always check the provider's own pricing page before you commit. Last checked 19 November 2026.

Five ways to cut your AI bill

  1. Use the smallest model that does the job. Small models are often 20 to 80 times cheaper and plenty for sorting, tagging and short replies.
  2. Keep prompts short. Long instructions are paid for on every single request.
  3. Cache repeated context. Most providers charge much less for input they have seen recently, such as a fixed system prompt.
  4. Batch work that can wait. Batch APIs typically cost about half the normal price, with results within a day.
  5. Limit the output length. Ask for short answers and set a maximum, since output tokens are the expensive part.

Sources

Where the formulas and figures on this page come from. We test every tool against worked examples from these before publishing.