← Back to Calculator

Claude Sonnet 4.6 vs GPT-5.6 Luna

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

Cost at a Glance

Claude Sonnet 4.6 is 2.6× more expensive than GPT-5.6 Luna — switching could save 62.2% on your monthly API bill.

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

Claude Sonnet 4.6$45.00/movsGPT-5.6 Luna$17.00/mo

Choosing GPT-5.6 Luna could save you $28.00/mo

Price Comparison (per 1M tokens)

Input (per 1M tokens)
$3.00vs$1.00
Output (per 1M tokens)
$15.00vs$6.00
Cache Write (per 1M tokens)
$3.75vs$1.25
Cache Read (per 1M tokens)
$0.30vs$0.10
Batch Input (per 1M tokens)
$1.50vs$0.50
Batch Output (per 1M tokens)
$7.50vs$3.00

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

Specifications

Context Window
1Mvs1M
Max Output Tokens
128Kvs64K
Knowledge Cutoff
2026-03vs2026-04
Modalities
Text, ImagevsText
Prompt Caching
YesvsYes
Batch API
YesvsYes
Thinking / Reasoning
YesvsNo

Benchmark Scores

SWE-bench Verified
79.6vs62.5
MMLU-Pro
85.2vs79.0
HumanEval
94.1vs89.5

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

Use Cases

Claude Sonnet 4.6

codinggeneralfast

GPT-5.6 Luna

fastcheapgeneral

About the Providers

Claude Sonnet 4.6 is developed by Anthropic. GPT-5.6 Luna is developed by OpenAI. This is a cross-provider comparison between Anthropic and OpenAI models. For the most up-to-date pricing, always check the official API documentation from each provider.

Compare More AI Models