Estimate what an AI feature will cost each month from your token usage, and compare the current API prices of Claude, GPT and Gemini models.
Loading the tool…
Current API prices (per million tokens)
| Model | Input | Output |
|---|---|---|
| Claude Fable 5.1 | $10 | $50 |
| Claude Opus 5.5 | $4 | $20 |
| Claude Sonnet 5.5 | $2 | $10 |
| Claude Haiku 5.5 | $0.10 | $0.50 |
| GPT-6 Astra | $10 | $50 |
| GPT-6.1 Sol | $2 | $10 |
| GPT-6.1 Terra | $1 | $5 |
| GPT-6 Luna | $0.10 | $0.50 |
| Gemini 3.1 Pro | $2 | $12 |
| Gemini 3.5 Flash | $1.50 | $9 |
| Gemini 3.1 Flash-Lite | $0.25 | $1.50 |
Standard list prices, checked 6 November 2026. Claude Haiku 5.5 rises to $0.50 / $2.50 for prompts over 100,000 tokens, and Gemini 3.1 Pro to $4 / $18 above 200,000.
How the cost is worked out
Cost per request = input tokens × input price + output tokens × output price, divided by one million. Multiply by requests per day and 30 days for a monthly estimate.
Ways to cut your bill
- Prompt caching: on Claude, cached input costs 5% of the normal price on Opus 5.5 and Sonnet 5.5, 10% on Haiku 5.5 and 2.5% on Fable 5.1.
- Batch processing: the Claude Batch API is 50% cheaper for work that doesn’t need an instant reply.
- Smaller models: route simple tasks to a cheaper model.
- Shorter outputs: output tokens usually cost 5 to 6 times more than input.
Frequently asked questions
How many words is a token?
In English, about 0.75 words, or 4 characters, per token. It varies by model and language.
Why do output tokens cost more?
Generating text takes more computing than reading it, so providers charge more for output.
Are these prices in US dollars?
Yes, before any taxes.
How often do prices change?
Often. Check each provider’s pricing page before committing to a budget.
Sources
Last updated: