Skip to content
Utkarsh Jaiswal

Free tool

Estimate your AI API spend in seconds.

Input your prompt and completion tokens to see exactly how much your LLM calls are costing you. Supports current pricing for the major AI providers.

Calculator component to be implemented in @/components/TokenCostCalculator

01

Pricing

Why token costs vary

Not all tokens are created equal.

Input vs Output

Almost every AI provider charges more for output tokens (completions) than input tokens (prompts). This is because generating a token is computationally more expensive than reading one.

Context Caching

Providers like Anthropic and Google now offer prompt caching, which significantly reduces the cost of repeating large system prompts across multiple requests.

02

Navigation

More cost calculators

Detailed breakdowns for specific providers.