OpenAI: GPT-5.6 Luna (batch) vs OpenAI: GPT-5.6 Sol (batch)

For a sample job of 1 million input tokens and 250,000 output tokens, GPT-5.6 Luna (batch) costs $0.25 and GPT-5.6 Sol (batch) costs $4.50, so GPT-5.6 Luna (batch) is about 18.0 times cheaper for the same work.

Both read up to 1,050,000 tokens at once, roughly 1,575 pages of text.

On our blended benchmark score GPT-5.6 Sol (batch) leads 99.3 to 89.4.

Across the 20 tasks where they differ, GPT-5.6 Luna (batch) scores higher on 7 (Code Completion, Code Documentation, Regex Writing and others), GPT-5.6 Sol (batch) on 13 (SQL Generation, Code Review, Code Refactoring and others).

Pick GPT-5.6 Luna (batch) if you need lower cost; pick GPT-5.6 Sol (batch) if you need benchmark performance.

Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.