OpenAI releases Decisions API beta with gpt-6-luna for typed answers
The Decisions API is in public beta and returns typed answers from text and images, with gpt-6-luna as the only model currently available.
On Zabio today
gpt-6-lunaLive. Call it by name with your Zabio key.Price and details
What changed
OpenAI released the Decisions API in public beta. It evaluates text, images, or both and returns typed answers. There are three question types: predicate returns a probability that a condition is true, choice selects one value from options you supply, and score rates input against ordered levels as a probability-weighted average. The model is gpt-6-luna, the only model currently available. Requests go to the POST /v1/decisions endpoint.
Key details
- The API is in public beta. General availability is planned for the coming weeks.
- Inputs can be a text string or user messages with text and images.
- Images must be inline base64 data URLs or public HTTP or HTTPS URLs. File IDs are not supported.
- Predicate answers return a probability from 0 to 1.
- Each question needs a unique name, and the response returns that name with its answer.
What it means for Zabio customers
Developers who need probabilities for yes or no conditions, fixed category choices, or ordered score levels can use this endpoint for those answer types. The source says to use Structured Outputs with the Responses API when you need your own JSON schema, or function calling when you need a tool call.
Source
Released the Decisions API in beta with gpt-6-luna. Turn text and images into typed answers 10x faster than the Responses API.
Original announcement: OpenAI API changelog
How it compares
The models in this story next to models of the same class at a similar price, all available with one Zabio key.
| Model | Input, $/M | Output, $/M | Cached, $/M | Context window | 1,000 calls | Fixing code, hard |
|---|---|---|---|---|---|---|
gpt-6-lunaOpenAIIn this story | 0.10 | 0.50 | 0.01 | 400,000 | $0.45 | 70.8 |
claude-haiku-5-5Anthropic | 0.10 | 0.50 | 0.01 | 1,000,000 | $0.45 | 77.6 |
llama-guard-4-12bMeta | 0.18 | 0.18 | no data | 131,072 | $0.45 | no data |
qwen3.5-9bQwen | 0.17 | 0.25 | no data | 262,144 | $0.47 | 9.2 |
Prices are the vendor list prices in USD per million tokens. "1,000 calls" is 1,000 requests of 2,000 input tokens and 500 output tokens each, without caching. Zabio bills the list price plus its service fee: see pricing.
Scores: percent correct for that kind of job, aggregated from public results by Epoch AI and LiveBench, read on 16 November 2026. Epoch AI: CC BY 4.0, LiveBench: Leaderboard results used with attribution; the 2.0 release states no terms of its own (read 2026-11-06); the first version's Mathematics, Language, IF results: Code Apache 2.0 and MIT; leaderboard results used with attribution
Source: OpenAI API changelog (2026-10-06)