LLM API cost calculator

How the cost is computed

Cost per request = (uncached input tokens × input price + cached input tokens × cache price + output tokens × output price) ÷ 1,000,000, with prices in dollars per million tokens. The monthly bill is that times your requests a month. Requests a day count 30 days to the month.

Cached input

Most makers bill input they serve from a prompt cache, such as a system prompt repeated on every request, at a fraction of the input price. The share you set applies to every model. A model with no published cache price bills those tokens at its input rate. Cache writes are left out.

Batch

Several makers sell a batch API that answers later, usually within 24 hours, at a lower rate. The table uses the standard rate. Each model page lists the batch terms its maker publishes.

AIGROW API credit

Credit runs some of these models at AIGROW rates, each below its maker’s list price. The credit column applies those rates to the same tokens, so the saving is the difference on your workload.

What is left out

Long prompt surcharges, priority and off-peak rates, regional pricing and cache writes, on both sides. The model pages list them.

OpenAI: API pricing, one of the price pages the list reads

• AI token counter

  Paste text into this AI token counter to see characters, words and tokens side by side, with exact counts for OpenAI’s GPT-5 models, labelled estimates for Claude, Gemini, Mistral and Llama, and the cost of each request.

• Context window checker

  Paste text or import a page into this context window checker to see which AI models can read it whole, how much room is left for the answer, and how much to cut when it does not fit.

• Agent cost calculator

  Use this AI agent cost calculator to price conversations from steps, tokens, cache hits and extra billed calls. Add tools and seats, compare annual budgets, and copy the breakdown.