Decisions API at a glance
The Decisions API, built on GPT-6 Luna, returns a probability, a choice or a score from text, images or JSON up to 10x faster than the Responses API. General availability adds prompt caching, JSON input and up to 400 questions per request. Output tokens are not charged.
Current standing
As of
- Rank
- #27of 43 models
GPT-6 Luna (Max) · 27.9 on the Artificial Analysis Intelligence Index v5.0.1 (opens in a new tab)
- Current leader
- Gemini 4 Carbon (Google) · 60
Computed from our daily snapshot; it changes as new models are measured. OpenAI makes the Decisions API generally available for fast classification and routing
What changed with Decisions API
On October 22, 2026, OpenAI made the Decisions API (POST /v1/decisions) generally available, about two weeks after its October 6 public beta. Developers define a question and its allowed answers, pass context as text, images or native JSON, and get back one of three typed answers: a probability that a condition is true, a choice from a fixed set, or a score against a rubric. It runs only on GPT-6 Luna, and OpenAI says it answers up to 10x faster than the same model through the Responses API.
General availability adds prompt caching for shared context, images inside individual questions, input_json for structured data, conversation history with tool calls, Private Link, and up to 400 questions per request, double the beta limit. A native GPT-Live integration lets a voice agent call Decisions directly. Pricing is $0.10 per million uncached input tokens and output tokens are not charged; ZDR, HIPAA use and US and EU regional processing are supported for eligible customers. Box, Datadog, Ramp, Sierra and Speak report faster routing or scoring in OpenAI's launch post.
Decisions API benchmarks and pricing
Values are copied from the linked source on the date shown. They are not IA Compa measurements.
- Input price per 1M tokens (uncached, Decisions API)as of · Source for Input price per 1M tokens (uncached, Decisions API): developers.openai.com (opens in a new tab)
- $0.10
- Output price per 1M tokens (Decisions API)as of · Source for Output price per 1M tokens (Decisions API): developers.openai.com (opens in a new tab)
- $0 (not charged)
Where to compare Decisions API
Independent leaderboards and official resources for comparing this model yourself. Rankings change often; each site shows its own current data.
General leaderboards
Why Decisions API matters for businesses
Many automations are a chain of small yes/no or pick-one calls: is this lead qualified, which team gets this ticket, is this document an invoice, should this agent action run. Moving those calls from a general chat model to Decisions can cut latency and cost while keeping the answer in a fixed format your workflow can branch on, which makes it a strong fit for intake forms, support triage and voice-agent routing.
Sources for this story
- Build more responsive apps with the Decisions API (opens in a new tab)Official
OpenAI · openai.com
- Decisions API guide (opens in a new tab)Official
OpenAI · developers.openai.com
- OpenAI API changelog (opens in a new tab)Official
OpenAI · developers.openai.com
Last verified: . IA Compa summarizes public announcements for business readers. We are not affiliated with the companies mentioned. Always confirm details, pricing, and availability with the official source.
- #openai
- #api
- #classification
- #routing
- #gpt-6
- #automation
