OpenAI Ships Agents API for Codex-Backed Cloud Agents
- Source
- x.com
- Date
Scaled agents on demand. This is pretty much the infrastructure that runs under the hood for ChatGPT Work, all wrapped up in an API which you can use to get started in < 1 min. Happy building. https://t.co/GhmuBkfjP1
Context
OpenAI's Tibo described the new Agents API as the infrastructure behind ChatGPT Work, now wrapped up for outside developers to call directly. OpenAI's announcement frames it as a public beta: agents can run autonomously for hours, execute code, use tools in parallel, and hand work off to sub-agents, all managed by OpenAI rather than assembled by the developer.
Developers choose between OpenAI-hosted sandboxes or partner infrastructure from providers such as Cloudflare, Vercel, or Oracle, and pay only for usage rather than a separate infrastructure fee. That billing model, and the option to swap in a different host, is what distinguishes this from simply calling a model API and building the yourself.
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
- agentic loop — The cycle an agent runs in: decide, call a tool, read the result, decide again — repeating until the goal is met or a stop condition fires.
- agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
Checking sign-in…
Loading comments…