OpenAI API
The OpenAI API is OpenAI's cloud application programming interface that lets developers call OpenAI's AI models and tools from their own software.
The OpenAI API is a cloud application programming interface that OpenAI offers to developers. Applications use it to call OpenAI's AI models and can combine them with built-in tools such as web search and file search.
The API comprises several interfaces, including the Responses API, which handles model response generation and tool calls in a single request format; the Agents API, which provides the Codex agent harness as a managed service; and the Decisions API, which returns a choice from a set of predefined answers.
This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.
Articles covering this entry
OpenAI's new Decisions API does not write answers.
The OpenAI Developers plugin lets Codex create and configure OpenAI API keys without sending you to a browser dashboard, which avoids lost keys and broken focus…
Engineers built the Decisions API quickly by using the internal Luna model with constrained sampling as a faster alternative to the Responses API.
Why OpenAI steers developers to the Agents API
The Decisions API uses Luna, a model described as fast and cost-effective for focused decisions.
OpenAI also introduced Decisions API, but its access timing and pricing remain unclear.