Anthropic · Medium · Updated 2026-11

Claude Sonnet 4 API Pricing & Cost Breakdown

Production software engineering, nuanced writing, complex code refactoring, and agentic tool use.

Input / 1M Tokens
$3.00
Cached Input / 1M
$0.300
Output / 1M Tokens
$15.00
Context Window
200K

Workload Cost Scenarios (30-Day Billing)

Prompt cache reads drop input cost by 90% ($0.30/1M) after initial cache write.

Scenario In / Out per Req Uncached Monthly 50% Cache Hit Monthly
Hobby / Prototype (100 req/day) 1500 / 400 $31.50 $25.43
Growing Startup (2,500 req/day) 2500 / 700 $1,350.00 $1,096.88
Production Scale (50,000 req/day) 3000 / 800 $31,500.00 $25,425.00

Compare Claude Sonnet 4 Against Alternatives

Lower-Cost Alternative Models

Gemini 2.0 Flash ($0.40/1M out) Qwen 2.5 72B ($0.40/1M out) Grok 3 Mini ($0.50/1M out) GPT-4o mini ($0.60/1M out)

Frequently Asked Questions

What is Claude Sonnet 4 API pricing per 1M tokens?

Standard input is $3.00/1M, cached input is $0.300/1M, and output is $15.00/1M.

What is the context window of Claude Sonnet 4?

Claude Sonnet 4 supports a 200K token context window with up to 64,000 max output tokens.

How much does prompt caching save on Claude Sonnet 4?

Prompt caching reduces cached input token rates by 90% compared with uncached input.

What workloads is Claude Sonnet 4 best suited for?

Production software engineering, nuanced writing, complex code refactoring, and agentic tool use.