OpenCraft

Model comparison

GPT-5.6 Luna vs GPT-6 Luna

Input price /M$0.10$0.052× cheaper
Output price /M$0.60$0.252.4× cheaper
Cache read /M$0.01$0.00502× cheaper
Context window1.1M1.1M
Catalog date9 Jul 202622 Sept 20262 mo newer

What the same turn costs

Estimates from published token rates — stated token counts, not measurements.

Quick answer2K tokens in, 600 outGPT-5.6 Luna$0.0006GPT-6 Luna$0.00032.2× cheaper
10-slide deck build60K tokens in, 9K outGPT-5.6 Luna$0.011GPT-6 Luna$0.00522.2× cheaper
150-page PDF read200K tokens in, 4K outGPT-5.6 Luna$0.022GPT-6 Luna$0.0112× cheaper

Capabilities

Bothtool-usevisionreasoning

GPT-5.6 Luna: file, image, text → text · GPT-6 Luna: file, image, text → text

Which model should you use?

Start with the token cost for your workload, the context you need, and supported input types. A lower price or larger context window does not establish better answer quality.

To compare answers, open each model in a separate chat and use the same prompt. Token tables use published specs and estimates; any measured AA results above are a separate benchmark.

Try GPT-5.6 Luna — pricing and availabilityTry GPT-6 Luna — pricing and availability