AI Model Pricing Calculator
Compare API costs across all major AI models. Input your token counts and see per-request and monthly cost estimates.
Compare API costs across all major AI models. Input your token counts and see per-request and monthly cost estimates.
AI API pricing is based on token usage, charged per million tokens. Most providers charge separately for input tokens (your prompt) and output tokens (the model's response). The total cost per request is the sum of input and output token costs.
The cheapest model depends on your use case. For simple tasks, smaller models like GPT-4.1 nano or Gemini 2.0 Flash offer the lowest per-token costs. For complex tasks requiring high quality, you may need more capable (and expensive) models. Use the calculator above to compare costs for your specific usage.
Prices shown are standard API rates and were last updated on the date shown at the bottom of the calculator. AI providers frequently adjust pricing, so check the provider's official pricing page for the most current rates. Volume discounts, batching, and prompt caching can also reduce costs.