How to use the LLM API Pricing Calculator
- 1. Describe your trafficEnter requests per day and the average input and output tokens per request.
- 2. Check the pricesPrices per million tokens are pre-filled for 12 models; edit any line or add your own.
- 3. CompareSee the cost per request and per month for each model, cheapest first.
How the cost is worked out
LLM APIs charge per token, with separate prices for input (your prompt, context and history) and output (the model's reply). Output is usually several times more expensive. For each model the calculator works out:
cost per request = (input tokens × input price + output tokens × output price) ÷ 1,000,000
If some input is served from a prompt cache, that share is charged at the cached price instead. The monthly cost is the cost per request × requests per day × days.
Worked example
With the defaults (2,000 requests a day for 30 days, 1,500 input and 400 output tokens each, no caching, ₹94 per US$), that's 60,000 requests, or 90 million input and 24 million output tokens. Claude Haiku 5.5 (for prompts up to 100k tokens) costs 1,500 × $0.10 + 400 × $0.50 = $350 per million requests, so $0.000350 per request and $21 a month (₹1,974). OpenAI's gpt-6-luna has the same listed prices, so it ties. Gemini 3.1 Flash-Lite comes next at $58.5 a month (₹5,499).
Prices and what's not included
The 12 pre-filled prices were copied from Anthropic's, OpenAI's and Google's official pricing pages on 7 November 2026, standard tier, text only. Prices change often, so treat them as a starting point and edit them to today's figures. Not included: GST, batch or priority tiers, long-context surcharges, cache-write fees, web search or tool fees, and image or audio tokens. Most importantly, test quality: the cheapest model is only a saving if it does the job.
Frequently asked questions
How do I know my token counts?
Use our LLM token counter on real prompts, or check the usage numbers your API returns. As a rough guide, one English word is about 1.3 tokens.
Why are Gemini cached prices blank?
Google prices context caching differently (including storage per hour), so we left it out; the calculator uses the normal input price for those lines.
Is the LLM API pricing calculator free?
Yes. You can open the LLM API pricing calculator and fill in everything without signing up. When you compare costs for the first time, we ask once for your name and WhatsApp number; after that it, and every other Uncodemy tool, opens straight away.