Tools Web

Calculators

Claude Token Cost Calculator

Estimate Anthropic Claude API spend from input and output tokens. Presets cover Fable 5.1 ($10/$50, cache hit $0.25/1M), Haiku, Sonnet, and Opus list rates; custom $/1M fields override. Cost = tokens ÷ 1M × price. Estimates only; Claude pricing pages prevail.

Math runs in your browser. Nothing is uploaded.

Custom $/1M rates (optional)

Estimated USD cost
—

Input cost
—

Output cost
—

Per 1k input tokens
—

Per 1k output tokens
—

Estimates only; official vendor pricing prevails (2026-10-30). Cost = tokens ÷ 1,000,000 × price per 1M.

OpenAI Token Cost Calculator · Gemini Token Cost Calculator · Grok Token Cost Calculator · LLM API Cost Calculator · AI Agent Cost Calculator

How it works

How is Claude token cost calculated?
Same formula as other API pages: tokens ÷ 1M × $/1M for input and output, then sum. Sonnet 5.5 at $2 / $10 with 100k in + 20k out ≈ $0.40.
Which Claude models are presets?
Fable 5.1 ($10 / $50 in/out; cache hit $0.25 / 1M when using prompt caching), Haiku 5.5 (≤100K prompt band), Sonnet 5.5, Opus 5.5, plus Haiku/Sonnet 4.5 and Opus 4.1 list bands. Override $/1M for other contracts.
What is Claude Fable 5.1 pricing?
Official list: $10 / $50 per 1M input/output. Prompt cache hits are $0.25 / 1M (0.025× input); 5-minute cache writes $12.50 and 1-hour writes $20 per 1M. Confirm on Anthropic’s pricing page.
Does Haiku pricing change above 100K prompts?
Yes. The preset uses the ≤100K band ($0.10 / $0.50). For longer prompts use the higher band in the custom fields.
Is Claude Pro included here?
No. This page is API token cost. Use the Claude Pro cost calculator for Pro/Max subscription totals.