OpenCraft

Model comparison

GPT-6 Luna vs GPT-6 Sol

Input price /M$0.0520× cheaper$1.00
Output price /M$0.2520× cheaper$5.00
Cache read /M$0.005020× cheaper$0.10
Context window1.1M1.1M
Catalog date22 Sept 202622 Sept 2026

What the same turn costs

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

Quick answer2K tokens in, 600 outGPT-6 Luna$0.000320× cheaperGPT-6 Sol$0.0050
10-slide deck build60K tokens in, 9K outGPT-6 Luna$0.005220× cheaperGPT-6 Sol$0.105
150-page PDF read200K tokens in, 4K outGPT-6 Luna$0.01120× cheaperGPT-6 Sol$0.22

Capabilities

Bothtool-usevisionreasoning

GPT-6 Luna: file, image, text → text · GPT-6 Sol: 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-6 Luna — pricing and availabilityTry GPT-6 Sol — pricing and availability