OpenAI API Pricing Calculator
Estimate a request with GPT-6 Astra, GPT-4o or GPT-4.1.
Rates and limits used
| Model | Input | Cached read | Cache write | Output | Context / output limit |
|---|---|---|---|---|---|
| GPT-6 Astra | $10 | $1 | $12.5 | $50 | 1,050,000 / 128,000 |
| GPT-4o | $2.5 | $1.25 | — | $10 | 128,000 / 16,384 |
| GPT-4.1 | $2 | $0.5 | — | $8 | 1,047,576 / 32,768 |
Prices are static per-million-token rates checked 2026-09-11. Astra requests above 272,000 input tokens use 2× input/cache rates and 1.5× output rates; Batch and Flex are 0.5×, and Fast is 2×. Confirm current terms before spending.
Use the calculator above for a quick local estimate. It does not call an API or send your token counts anywhere. The supported models are GPT-6 Astra, GPT-4o and GPT-4.1.
The calculation is: (total input − cached reads − cache writes) × input rate + cached reads × cached-input rate + cache writes × cache-write rate + output × output rate, divided by 1,000,000. Cached reads and cache writes are disjoint subsets of total input. This estimate excludes tool-call charges, taxes and regional fees.
The estimate uses the published model rates and limits shown in the expandable rate table. Provider pricing, account eligibility and taxes can change; confirm the linked official pages before committing spend.