OpenAI Launches Agents API in Public Beta: One API Call Now Powers the Codex Harness
OpenAI has released the Agents API in public beta, giving developers direct access to the same harness and infrastructure that power Codex. OpenAI hosts and maintains the harness, while developers can run the agent's compute in an OpenAI-managed sandbox, their own infrastructure, or a partner sandbox.
Is it deployable? Yes. The Agents API is live for all developers in public beta. Data remains US-only, and Zero Data Retention is not supported.
What OpenAI Shipped
The Agents API is a managed service built on the open-source Codex harness. According to the OpenAI team, scaling Codex and ChatGPT for Work revealed what long-running agents actually need: a harness that manages context, uses tools efficiently, and coordinates subagents, plus infrastructure that keeps them running reliably for days.
The official documentation organizes the API around four core concepts:
- Agent: The model, instructions, tools, and MCP servers available to it.
- Environment: An optional sandbox where the agent accesses files, loads skills, and runs commands.
- Session: A durable agent instance that works on tasks and responds to input.
- Events and items: The inputs sent to the agent and the output it produces.
A session runs in four steps: you create it and assign a task, follow progress through streaming or webhooks, then continue with a new task or steer the current turn.
One API Call
OpenAI's announcement demonstrates an incident-investigation agent created in a single API call, showcasing how the Codex harness can be deployed without managing the underlying orchestration infrastructure.
2026 Context
The launch arrives as agentic AI frameworks mature rapidly through 2026, with enterprises demanding production-grade reliability for agents that run continuously rather than in single-turn interactions. By abstracting the Codex harness into a managed API, OpenAI positions itself against competing agent orchestration platforms while addressing a key pain point: developers previously had to build their own context management, tool-use loops, and subagent coordination from scratch. The US-only data residency and lack of Zero Data Retention support, however, may limit adoption among regulated industries with stricter compliance requirements.
via MarkTechPost