Why it mattersA team can now release a background agent without writing the loop that survives compaction, tool retries, and multi-turn state, because that layer moves from the team's code to an OpenAI-billed API.
OpenAI opened the Codex harness to third-party applications on Thursday as the Agents API, a managed service that OpenAI's own documentation describes as giving an application "access to the Codex harness through an OpenAI-managed API". The same harness that runs Codex is now available through a public endpoint, and OpenAI handles the pieces most teams have been writing themselves: sessions, orchestration, context compaction and recovery. The Hacker News thread on the developer docs reached 65 points in about three hours.
What a session actually is
The Agents API is built around a session, which the docs define as "a durable instance of an agent that works on tasks and responds to input". A session holds state across turns, so a team does not rebuild the conversation and tool history on every request. Sessions go through a fixed lifecycle: creation, task assignment, progress monitoring, then continuation or redirection across more turns. Every code example in the overview page uses the model gpt-6-astra.
Agents inside a session run in a sandbox that can execute code, edit files, and connect to servers over the Model Context Protocol. The tools the docs list are programmatic tool calls, MCP server connections, a built-in web search, and artifact production. An agent can spawn subagents up to a configurable limit shown in the docs as max_concurrent_subagents: 4.
Pricing, residency, and a real constraint
OpenAI's pricing statement on the page is short. Model use is billed at the selected model's API rates, OpenAI-provided tools use standard rates, and OpenAI-hosted sandboxes are billed at standard container rates. Commenters on Hacker News reported that the sandbox meter runs in twenty-minute blocks, which is worth knowing before using many parallel sessions for a small task.
Two constraints in the docs will decide whether some teams can use the service at all. Data residency for the Agents API is currently the United States only, and Zero Data Retention is not supported, including when the sandbox is self-hosted. A team on a European data agreement or a contract that requires ZDR cannot put this into production today, even with its own execution environment.
The other important decisions are about the tools. A team still writes and hosts the tools the agent calls, and still provides an execution environment for anything it does not want running in an OpenAI sandbox. What OpenAI takes over is the loop between those pieces: the state that has to survive a short network failure, the compaction of a long conversation, the recovery when a step fails and the agent has to try something else.
That loop is the part every team building an agent has been rewriting for a year. Moving it to a managed API means an application can release a background agent without owning the harness code, and pay OpenAI directly for the compute the agent uses. The trade-off is the one the docs already state openly: US residency, no ZDR, and a sandbox meter someone has to watch.
Source
OpenAI developer docs: Agents API overview, and OpenAI: Introducing the Agents API.
This item was written by an AI system from the linked source. Reveneau is responsible for what it publishes.
Get AI News in your inbox
New developer tools, model and agent releases, and how teams are actually using them to release software. Short, and only when there is something worth reading.
