A practical LLM cost simulator for builders.

llmcalc.app compares recorded Claude Code usage with subscription prices. Import a ccusage report, review its API-equivalent value and assumptions, and export a dated receipt. Your report stays in your browser. Supporting tools model caching, batch processing and agent loops.

What this is

• A Claude Code comparison with explicit pricing coverage and limit context.
• A multi-model token counter that runs entirely in your browser.
• A cost calculator with explicit input, output, caching, batch and long-context assumptions.
• Three differentiated calculators: prompt-caching ROI, batch decision tool, and a multi-turn agent-loop simulator with workload templates.
• Model and comparison reference pages, all driven from a single models.json.

What it isn't

• A replacement for your provider's invoice. Always reconcile against the real bill.
• A live monitor. Pricing data is verified periodically, not in real time.
• Affiliated with OpenAI, Anthropic, Google, or Meta. We're a third party.

How the data is kept honest

Every model in our index carries two things you should look at: a last_verified date and a confidence flag (official or inferred). The changelog tracks pricing changes and verification dates publicly.

Spot a wrong number? Use the report incorrect price link in the footer (or anywhere on the site). The mailto template prefills model, field, and source so it takes 30 seconds. Goes straight to the maintainer's inbox.

Tracked models

Currently 38 tracked models across Anthropic, OpenAI, Google, Groq, and xAI, including reference models. Each row has its own verification date. See the full list.

Use our data

The full pricing dataset is free at /api/pricing.json: every model, cache tiers, batch discounts, long-context tiers, and a last-verified date per row. It regenerates from the same source file the site renders from, so it can never drift from what you see here. Use it in your tools with attribution; a link back to llmcalc.app is appreciated. There is also an llms.txt and a llms-full.txt for AI assistants.

Tech

Static site (Astro + Tailwind). Tokenization runs client-side via tiktoken-class libraries. No analytics cookies. Privacy-respecting traffic counts via Cloudflare Web Analytics.