BeavBeav

OpenAI · Decision models

GPT-6 Luna Decisions

Classifies, scores and estimates probabilities from input, returning structured decisions.

Pricing

Charged by actual usage

Unit: points / 1M tokens

Input per request≤ 272K

Input
168≈ $0.336
Cache hit
17≈ $0.034

Input per request> 272K

Input
336≈ $0.672
Cache hit
34≈ $0.068
  • Tiered pricing: the tier is picked by the input length of each request. Whichever tier a request’s input tokens fall into, its input, cache and output are all billed at that tier’s prices, not split across tiers.
  • Cache hit: a prefix repeated from earlier requests (such as a system prompt or a long document you keep referring to) is cached, and the cached part is billed at the cache price, about 10% of the input price.
  • Billed by input tokens only.

This model has no member discount; members pay the list price. See plans

About this model

Classifies, scores and estimates probabilities from input, returning structured decisions. Pick this model in Beav to use it; points are charged at the prices above.

Use in Beav

  1. 01Download Beav and sign in
  2. 02Choose GPT-6 Luna Decisions in the model picker
  3. 03Use it for classification, scoring and probability estimates
View all