AI cost calculator
OpenAI API pricing calculator
Your monthly OpenAI API bill for each current GPT model at OpenAI's list price. GPT-6.1 Sol costs $2 per million input tokens and $10 per million output tokens; Batch and Flex cost half, Fast mode twice.
Your inputs
Result
$2,130 a month on GPT-6.1 Sol
$7.10 per 1,000 requests.
- Cost per request
- $0.0071
- Cost per 1,000 requests
- $7.10
- Per month
- $2,130
- Per year
- $25,560
- Saved by prompt caching
- $570.00 a monthagainst the same requests with no cache hits
- Cheapest OpenAI model for this workload
- GPT-6 Luna$108.00 a month
Worked examples
Each row is the calculator run on the inputs shown, with every other input at its default.
| Workload | Model | Requests a day | Tokens in / out | Per month |
|---|---|---|---|---|
| Support chatbot | GPT-6 Astra | 5,000 | 3,000 / 300 | $751.50 |
| Support chatbot on GPT-6 Luna | GPT-6 Luna | 5,000 | 3,000 / 300 | $39.15 |
| Classification at scale on Luna | GPT-6 Luna | 200,000 | 400 / 5 | $147.00 |
| Overnight batch on Terra | GPT-6.1 Terra | 5,000 | 20,000 / 1,000 | $1,875 |
| Coding agent on GPT-6 Astra | GPT-6 Astra | 2,000 | 60,000 / 2,000 | $12,840 |
| Coding agent on GPT-6.1 Sol, Fast mode | GPT-6 Astra | 2,000 | 60,000 / 2,000 | $4,488 |
How it is calculated
OpenAI bills input, cached input and output tokens separately, each at a price per million tokens. Cached input costs a tenth of the input price on GPT-6.1 Sol, Terra and GPT-6 Astra and Luna.
Prices are the Standard tier for short contexts. Batch and Flex are half the Standard price, Fast mode (formerly Priority processing) is twice. Ultrafast mode is six times Standard and only available on GPT-6 Astra and GPT-6.1 Sol, so it is not in the menu.
OpenAI also charges for writing to the prompt cache: on GPT-6.1 Sol $2.50 per million tokens for a 30-minute write and $5 for a 12-hour write. For a prompt reused many times that cost is small and is left out here.
GPT-5.6 Sol is listed at its promotional price, which OpenAI says runs at least through November 21, 2026.
Questions
How much does the OpenAI API cost?
Per million tokens at the Standard tier: GPT-6 Luna $0.10 input and $0.50 output, GPT-6.1 Terra $1 and $5, GPT-6.1 Sol $2 and $10, GPT-6 Astra $10 and $50. Cached input is a tenth of the input price.
What is the difference between Batch, Flex and Fast?
Batch and Flex trade speed for a 50% discount. Fast mode, which OpenAI renamed from Priority processing on July 30, 2026, costs twice the Standard price for faster responses.
Is the OpenAI API the same price as ChatGPT?
No. ChatGPT and Codex plans are flat monthly prices with usage limits and credits; API usage is billed per token. The Codex pricing calculator compares the two.
Do reasoning tokens cost extra?
They are billed as output tokens. Add them to the output tokens per request if the model reasons before it answers.
Which OpenAI model is cheapest?
GPT-6 Luna, at $0.10 per million input tokens and $0.50 per million output tokens.
Sources
- OpenAI: API pricing, checked 2026-10-29
Prices and plans change. This page was last checked on 2026-10-29. The data is open: llm-prices.json (CC BY 4.0).