ANTHROPIC CLAUDE API · USAGE-AWARE

Claude API Cost Calculator

Estimate Claude Sonnet 5.5 costs from writing, summarization, coding, or research tasks—or enter measured tokens for caching, Batch, and inference-geography pricing.

Official Anthropic pricingVerified October 11, 2026USD · First-party Claude API
Pricing mode
SIMPLE ESTIMATE

Tell us what you do

Based on observed usage samples and official pricing. Switch to measured usage when you have response usage fields.

SAME TASK · OFFICIAL PRICING

Compare estimated cost ranges

These ranges use each measured model’s observed usage for the same task, size, and count. They do not compare quality or speed.

OpenAI · GPT-6 Astra$1.08–$1.09No positive savings range
OpenAI · GPT-6.1 Sol$0.22–$0.23Potential monthly savings: $0.15–$0.21
OpenAI · GPT-6 Luna$0.010–$0.013Potential monthly savings: $0.36–$0.41
Claude · Opus 5.5$0.87–$0.92No positive savings range
Claude · Haiku 5.5$0.015–$0.018Potential monthly savings: $0.36–$0.41
Google · Gemini 4 Argon$0.25–$0.26Potential monthly savings: $0.12–$0.17
Google · Gemini 3.8 Flash$0.27–$0.32Potential monthly savings: $0.06–$0.15
Google · Gemini 3.6 Flash$0.29–$0.33Potential monthly savings: $0.05–$0.13

CLEAR PRICING MATH

How Claude API cost is calculated

Each usage category stays separate, so cache writes and cache hits are not mistaken for ordinary input.

input + output + cache writes + cache reads

Batch applies a 50% discount. US-only inference applies a 1.1× multiplier to all token categories.

01

Input and output

Input and generated output use separate per-million-token rates. Copy actual counts from the API response for a workload-specific estimate.

02

Prompt caching

A 5-minute write costs 1.25× base input and a 1-hour write costs 2×. Cache reads are cheaper, but savings require enough reuse.

03

Batch processing

Anthropic publishes a 50% discount for asynchronous Batch workloads. It is a cost option, not an equivalent low-latency replacement.

QUICK EXAMPLES

Example monthly workloads

Claude Sonnet 5.5 · Standard

1M input + 200k output

$4.00 / month
Claude Sonnet 5.5 · Batch

1M input + 200k output

$2.00 / month
Claude Haiku 5.5 · Cached

100k 5m write + 1M cache reads

$0.02 / month

For the most accurate result: use input_tokens, output_tokens, cache_creation_input_tokens, and cache_read_input_tokens from the Claude API response. Free credits, taxes, and negotiated pricing are not treated as public fixed rates.