← Back to Calculator

Claude Haiku 4.5 vs Claude Sonnet 4.6

Detailed comparison of API pricing, technical specifications, and benchmark scores. Updated 2026-06-29.

Cost at a Glance

Claude Sonnet 4.6 is 3× more expensive than Claude Haiku 4.5 — switching could save 66.7% on your monthly API bill.

At 5M input + 2M output tokens per month:

Claude Haiku 4.5$15.00/movsClaude Sonnet 4.6$45.00/mo

Choosing Claude Haiku 4.5 could save you $30.00/mo

Price Comparison (per 1M tokens)

Input (per 1M tokens)
$1.00vs$3.00
Output (per 1M tokens)
$5.00vs$15.00
Cache Write (per 1M tokens)
$1.25vs$3.75
Cache Read (per 1M tokens)
$0.10vs$0.30
Batch Input (per 1M tokens)
$0.50vs$1.50
Batch Output (per 1M tokens)
$2.50vs$7.50

Prices are per 1 million tokens. Actual costs depend on your monthly token volume. Use the calculator →

Specifications

Context Window
1Mvs1M
Max Output Tokens
64Kvs128K
Knowledge Cutoff
2026-03vs2026-03
Modalities
Text, ImagevsText, Image
Prompt Caching
YesvsYes
Batch API
YesvsYes
Thinking / Reasoning
NovsYes

Benchmark Scores

SWE-bench Verified
55.3vs79.6
MMLU-Pro
76.8vs85.2
HumanEval
88.2vs94.1

Benchmark scores from official provider reports. Higher is better. Missing scores indicate the provider has not published that benchmark yet.

Use Cases

Claude Haiku 4.5

fastcheapgeneral

Claude Sonnet 4.6

codinggeneralfast

About the Providers

Claude Haiku 4.5 is developed by Anthropic. Claude Sonnet 4.6 is developed by Anthropic. Both models are from the same provider, representing different tiers in the Anthropic model lineup. For the most up-to-date pricing, always check the official API documentation from each provider.

Compare More AI Models