Free Tool

AI API Cost Calculator

Toggle between OpenAI, Anthropic, Google, xAI and Meta — pick a model tier, enter your usage, and watch the cost update live. No signup, everything runs in your browser.

Your usage

Model

Avg input tokens per request

Avg output tokens per request

Requests per day

—

estimated per month

per request

per day

per year

Live comparison — all 5 providers

Same usage, side by side. Updates instantly as you type.

Pricing verified October 2026 from provider pricing pages and API docs (per 1M tokens, standard tier, USD). Rates refresh daily at midnight US Eastern. Prices change — always confirm on the provider's own pricing page before budgeting. Estimates exclude prompt caching, batch discounts and taxes. Cached input is typically ~90% cheaper where supported.

FAQ

Why is output priced higher than input?

Generating tokens costs providers more compute than reading them. Output rates run roughly 3–6× input rates across providers.

How do I cut my API bill?

Route simple tasks to mini/flash-tier models, enable prompt caching for repeated system prompts, use batch APIs for non-urgent work (up to 50% off), and cap max output tokens aggressively.

Which provider is cheapest?

It depends on the tier. Budget tiers (GPT-6 Luna, Gemini Flash-Lite) cost cents per million tokens; flagships (GPT-6 Astra, Claude Fable 5.1) cost 100× more. Toggle above with your real usage to see.

Why is Meta priced via Together AI?

Meta gives Llama away as open weights and sells no API directly. To use Llama via API you pay a hosting provider — Together AI is one of the most popular, and its rates are what the Meta tab uses.