How to use this tool
- Pick a model — the input and output prices fill in automatically.
- Enter your estimated monthly input tokens (your prompts) and output tokens (the model's replies).
- Read your estimated monthly bill. Choose Custom prices to enter exact rates.
2026 model pricing (per 1M tokens)
API bills are split into input tokens (what you send) and output tokens (what the model generates), each priced separately. Current public rates:
- OpenAI GPT-5.5 — $5 input / $30 output
- Claude Opus 4.8 — $5 input / $25 output
- Claude Sonnet 4.6 — $3 input / $15 output
- Claude Haiku 4.5 — $1 input / $5 output
- OpenAI GPT-4o — $2.50 input / $10 output
- OpenAI GPT-4o mini — $0.15 input / $0.60 output
- Gemini 2.5 Pro — $1.25 input / $10 output
cost = (input tokens ÷ 1M × input price) + (output tokens ÷ 1M × output price)
Example
On GPT-5.5 with 2M input and 1M output tokens: (2 × $5) + (1 × $30) = $40/month.
Frequently asked questions
Why are input and output tokens priced differently?
Generating output is more compute-intensive, so output costs more. Output is often the bigger part of your bill.
What is a token?
A token is a chunk of text — roughly 4 characters or about 0.75 words in English. Prompts and replies are both counted in tokens.
Are these prices official?
They reflect public 2026 rates and can change. Confirm current pricing on the provider's site, and use Custom to enter exact figures.
Disclaimer: Estimates only. Model prices change frequently and may exclude discounts (batch, cached input) or extra fees. Always verify current pricing with OpenAI, Anthropic, or your provider. Not financial advice.