OpenAI Developer platform adds Decisions API testing interface
BIBIBI
AT A GLANCE
The report said that the OpenAI developer platform has added a Decisions API testing interface for judgment, selection, and scoring.
Article
OpenAI Developer platform adds Decisions API testing interface, supporting judgment, selection, and scoring
PANews October 20 reported, according to TestingCatalog, that OpenAI Developer platform adds Decisions API testing interface, allowing users to test Predicate、Choice and Score modes, used respectively to estimate the probability that a condition is true, select from given options, and assign scores according to scoring criteria.OpenAI Official documentation shows that this API is currently in public beta, supports text and image inputs, and can be used for content classification, request routing, and task-priority determination. It currently supports only the gpt-6-luna model, with a base input price per million Token 0.10 USD, with no output Token fee.
PANews, citing TestingCatalog, reported that OpenAI the developer platform has added a Decisions API testing interface.
02
The report said that users can test Predicate、Choice and Score modes.
03
The original report stated that the modes are respectively used to estimate the probability that a condition is true, select from given options, and assign scores according to scoring criteria.
04
The original report cited OpenAI official documentation as saying that this API is currently in public beta and supports text and image inputs.
05
The report said that this API can be used for content classification, request routing, and task-priority determination.
06
The report said that this API currently supports only the gpt-6-luna model, with a base input price per million Token 0.10 USD, with no output Token fee.
AI-assisted interpretation
The following is analysis, separate from reported facts. Verify important claims independently.
This is a developer-oriented decision-making interface:Predicate used to assess the likelihood that a condition is true,Choice used to select from given options,Score and used to score according to criteria. The report also said that it can accept text and images.
Why it matters to readers
If the report is accurate, developers can use a unified interface to handle tasks such as classification, routing, and priority determination.
Beginners can understand it as a API testing feature that helps applications “judge, select, and score”; before use, they should verify access eligibility, supported models, and pricing.
Risks and unknowns
The evidence does not provide a OpenAI link to official documentation, and its public-beta status still requires verification.
Only gpt-6-luna, input capabilities, and pricing information still require verification through official pages.
The original report does not specify available regions, access eligibility, or the official launch date.
Related Developments
Loading event timeline…
Related concepts
API
This term is not in the glossary yet. Browse related concepts in the glossary.
