World of the Developers
All calculators

Claude API Cost Calculator

Calculate Anthropic Claude API costs across Opus, Sonnet, and Haiku for your exact token usage.

Usage

$5.00/M in · $0.50/M cached in · $25.00/M out · 1M context

Estimated cost

$525.00/month

Per request

$0.0175

Per day

$17.50

Per year

$6,387.50

Compare across models

ModelProviderPer month
OpenAI$7.50
OpenAI$13.50
OpenAI$24.00
OpenAI$36.00
OpenAI$37.50
OpenAI$37.50
Google$46.50
Google$78.75
Anthropic$105.00
OpenAI$180.00
OpenAI$180.00
Google$180.00
OpenAI$187.50
Anthropic$210.00
OpenAI$225.00
OpenAI$240.00
Google$240.00
Anthropic$315.00
OpenAI$420.00
Anthropic$525.00
Anthropic$525.00
Anthropic$525.00
Anthropic$1,050.00

How this is calculated

Providers bill input and output tokens separately, per million tokens (MTok). Cached input tokens — a repeated prompt prefix the provider recognizes — are billed at a discounted rate.

cost = (input_tokens − cached_tokens) × input_rate
     + cached_tokens × cached_rate
     + output_tokens × output_rate

Pricing is verified against provider pricing pages as of 2026-09-01. AI and cloud pricing changes frequently — confirm the current rate on the provider's own pricing page before budgeting.

Frequently asked questions

What's the price difference between Claude Opus, Sonnet, and Haiku?

Claude Opus 5 ($5/$25 per MTok input/output) is Anthropic's flagship for complex agentic and coding work; Sonnet 5 ($2/$10) balances cost and capability for everyday tasks; Haiku 4.5 ($1/$5) is the fastest and cheapest tier, suited to high-volume, latency-sensitive workloads.

How much does Claude prompt caching save?

Anthropic prices cached input tokens at roughly 10% of the standard input rate — for Claude Opus 5 that's $0.50/MTok cached versus $5.00/MTok standard, a meaningful saving for repeated system prompts or long reference documents.

What is Claude Fable 5?

Claude Fable 5 is Anthropic's most capable widely released model, priced above Opus 5 at $10/$50 per MTok, intended for the most demanding reasoning and long-horizon agentic work.

Does Claude pricing differ on AWS Bedrock or Google Vertex AI?

Anthropic's first-party API rates (used in this calculator) also apply on Microsoft Foundry. Amazon Bedrock and Google Vertex AI are partner-operated with separate pricing — check AWS's or Google Cloud's pricing pages for those rates.