OpenAI Decisions API is generally available with gpt-6-luna at USD $0.10 per 1M uncached input tokens, $0.01 per 1M cached-read tokens and no output-token charge; cache writes are billed at the standard model rate. POST /v1/decisions supports up to 400 typed questions per request, shared-input caching, JSON and image inputs; regional and long-context premiums may apply.
Secondary price terms only; primary pricing stays in the deal summary.
Use-case fit and limitations from the existing resource record.
Decisions endpoint-specific maximum context size is unconfirmed; long-context input and regional processing premiums apply. Prompt cache writes are billed (not free); do not assume the 1.05M model window is the Decisions endpoint request limit.
Available
Non-price resource facts only; pricing, history, and evidence stay in their own sections.
Decision visuals remain traceable to the existing source and verification record.
Independent ranking · native prices · evidence-linked · commercial relationships isolated from scoring and publication.