How this calculator works
| Metric | Formula |
|---|---|
| Monthly requests | requests per day × days per month |
| Input cost | input tokens × (1 − cached %) × input price ÷ 1M + input tokens × cached % × cached price ÷ 1M |
| Output cost | output tokens × output price ÷ 1M |
| Monthly cost | monthly requests × (input cost + output cost per request) |
Worked example
With these inputs:
- Model: OpenAI — GPT-6.1 Sol
- Requests per day: 1,000
- Input tokens per request: 1,500
- Output tokens per request: 400
- Input served from prompt cache: 0%
- Days per month: 30
Estimated monthly API cost: $210. 30,000 requests a month on GPT-6.1 Sol cost about $210 ($2,520 a year).
| Cost per request | $0.00700 |
|---|---|
| Cost per day | $7.00 |
| Cost per year | $2,520 |
| Input tokens per month | 45M ($90.00) |
| Output tokens per month | 12M ($120) |
Open this example in the calculator
Current API prices per million tokens
Standard (pay-as-you-go) tier for prompts in the short-context range, checked on 5 October 2026 against each provider’s official pricing page. Prices change often; always confirm before committing to a budget.
| Provider | Model | Input | Cached input | Output |
|---|---|---|---|---|
| OpenAI | GPT-6 Astra | $10.00 | $1.00 | $50.00 |
| OpenAI | GPT-6.1 Sol | $2.00 | $0.10 | $10.00 |
| OpenAI | GPT-6 Luna | $0.10 | $0.01 | $0.50 |
| Anthropic | Claude Fable 5.1 | $10.00 | $0.25 | $50.00 |
| Anthropic | Claude Opus 5.5 | $4.00 | $0.20 | $20.00 |
| Anthropic | Claude Sonnet 5.5 | $2.00 | $0.20 | $10.00 |
| Anthropic | Claude Haiku 4.5 | $1.00 | $0.10 | $5.00 |
| Gemini 3.1 Pro (preview) | $2.00 | $0.20 | $12.00 | |
| Gemini 3.8 Flash | $0.75 | $0.075 | $3.75 | |
| Gemini 3.5 Flash-Lite | $0.30 | $0.03 | $2.50 |
What drives LLM API cost
- Output tokens: they cost several times more than input, so long answers and visible reasoning add up fastest.
- Context size: retrieval (RAG) and chat history are resent on every request. Trimming context is usually the biggest saving.
- Model choice: small models such as GPT-6 Luna, Gemini Flash-Lite and Claude Haiku cost 10–100 times less than flagship models and handle classification, extraction and routing well.
- Prompt caching: repeated prefixes such as a long system prompt are billed at a fraction of the input price.
- Batch processing: work that can wait a few hours is typically billed at half price.
How to estimate tokens for your use case
- Count the words in a typical system prompt, retrieved context and user message, then divide by 0.75 to get input tokens.
- Do the same for a typical answer to get output tokens; add reasoning tokens if you use a thinking model.
- Multiply by expected daily requests, then run the numbers above for two or three candidate models.
- After launch, log real token counts from the API response and update the estimate.
Open this calculator with your numbers
Every option can be set in the web address, so you can bookmark a scenario or send it to a colleague. AI assistants such as ChatGPT, Gemini, Claude and Perplexity can use the same parameters to open this calculator with your numbers and the result already on the page.
| Parameter | What it sets | Accepted values |
|---|---|---|
model |
Model | one of gpt-6-astra, gpt-6.1-sol, gpt-6-luna, claude-fable-5.1, claude-opus-5.5, claude-sonnet-5.5, claude-haiku-4.5, gemini-3.1-pro, gemini-3.8-flash, gemini-3.5-flash-lite |
requests |
Requests per day | number from 1 to 100000000, default 1000 |
input_tokens |
Input tokens per request | number from 0 to 200000, default 1500 |
output_tokens |
Output tokens per request | number from 0 to 128000, default 400 |
cached |
Input served from prompt cache | number from 0 to 100 (%), default 0 |
days |
Days per month | number from 1 to 31, default 30 |
Also available as plain text for AI assistants and a free JSON API (OpenAPI spec).
Sources
Last reviewed by the Infikey Technologies team.
Disclaimer
This calculator is provided free for general information and planning only. Results are estimates based on the inputs you enter and the assumptions described on this page, reference data such as published prices may change, and actual costs and outcomes will differ. Nothing on this page is financial, legal, tax, investment or other professional advice. Infikey Technologies Private Limited, Infikey Technologies LLC and their directors, employees and affiliates make no warranty, express or implied, about the accuracy, completeness or suitability of this tool or its results, and accept no liability for any loss or damage, direct or indirect, arising from its use or from reliance on its results. Verify all figures independently and seek professional advice before making any decision. Use of this tool is at your own risk.