GPT-6 Luna

gpt-6-luna sits alongside claude-sonnet-5, claude-opus-4-6, deepseek-v4-pro in the catalog. Compare them on the dimensions that change your bill and your users’ experience: task quality on your own prompts, latency at your concurrency, context and output limits, and cost per completed task rather than per token.

Before switching production traffic to gpt-6-luna, run a pilot on a representative slice of your traffic and check output quality, latency at peak concurrency, and cost per request. Verify the error and retry behaviour, and confirm the request limits you depend on match your plan.

Reasoning tokens are billed as output on gpt-6-luna, at $0.5 per 1,000,000 token. They are generated before the visible answer and count toward both latency and spend, so a higher reasoning setting costs more even when the final answer is short.

gpt-6-luna is a reasoning model. Reasoning effort can be tuned per request. Lower effort settings cut reasoning tokens and cost for routine work; reserve higher settings for problems that need deeper search. Measure quality at two or three settings before fixing one in production.

Recorded results for gpt-6-luna: aa_intelligence_index 62.7; arena_text 88.1. Benchmark positions are a coarse filter only — run your own prompts against the candidate models before you commit, because ranking shifts with task shape and prompt style.