OpenAI API Cost Calculator
Estimate OpenAI GPT API costs by input tokens, output tokens, cached input tokens, API calls, and billing period.
Use the AI API Cost CalculatorWhat This Calculator Helps Estimate
- Input token cost for prompts and context.
- Output token cost for generated responses.
- Cached input token cost when prompt caching applies.
- API calls, monthly spend, and yearly planning ranges.
Supported Models
- GPT-5.5
- GPT-5.4
- GPT-5.4 Mini
How Cost Is Calculated
Total cost = Input cost + Cached input cost + Output cost
Use the main calculator to enter token volume and call count. It applies USD pricing per 1M tokens and separates input, cached input, and output costs.
Pricing Note
Pricing data is organized from official provider pages for reference. OpenAI pricing can change, so always verify the latest pricing from the official OpenAI API pricing page before making production decisions.
Common Use Cases
- AI coding assistants
- Customer support chatbots
- AI agents
- Long-form writing assistants
- Production API cost planning
FAQ
How are OpenAI API costs calculated?
OpenAI API costs are estimated by multiplying input, cached input, and output tokens by their USD price per 1M tokens, then multiplying by API call volume.
Why do output tokens usually cost more than input tokens?
Output tokens require model generation work, so provider pricing often assigns a higher rate to generated tokens than to prompt tokens.
What are cached input tokens?
Cached input tokens are repeated prompt or context tokens that may qualify for a lower cached input price when provider caching is used.
Is this OpenAI pricing always up to date?
No. This page provides a reference view and should be checked against official OpenAI pricing before production budgeting.