AIToday
Large Language ModelsAI Coding AssistantsTHE DECODERPublished: Sep 11, 2026, 19:01 JST2 min read

OpenAI opens Agents API beta, same infra as Codex

OpenAI opens Agents API beta, same infra as Codex

3 Key Points

  1. What happened

    OpenAI released the Agents API as a public beta. It runs on the same infrastructure as Codex and ChatGPT, with automatic context management, parallel tool use, and task delegation to sub-agents.

  2. Why it matters

    Developers can now choose OpenAI-hosted sandboxes or partners like Cloudflare, Vercel, and Oracle, with no extra fees beyond token usage. This builds on the open-source Codex harness and supports MCP, custom functions, and web search.

  3. What to watch

    The test is whether developers adopt the partner sandboxes for production workloads, since billing is based solely on token usage. Watch how the public beta develops.

WHO IT HITSThird-party developers and enterprise engineering teams building cloud-based AI agents gain a new option for autonomous, long-running tasks with flexible sandbox hosting.

Ask the AI about this article →

Summaries like this, in your inbox every morning.

Context & Analysis

OpenAI is opening up the infrastructure behind its own flagship coding and chat products, Codex and ChatGPT, to outside developers. Until now, the same long-running agent capabilities that power those products were not directly available through a public API. Building on the open-source Codex harness means developers get a familiar foundation, while support for MCP, custom functions, and built-in tools like web search reduces the amount of plumbing they need to do themselves.

The choice between OpenAI-hosted sandboxes and partners like Cloudflare, Vercel, and Oracle gives teams flexibility in where their agents actually run. There are no extra fees beyond token usage, which simplifies cost planning for projects that might run agents for hours at a time. The public beta status suggests OpenAI is still gathering feedback before a wider rollout.

The stakes here hinge on whether third-party developers adopt the partner sandboxes for production workloads. If they do, it could accelerate the shift toward cloud-based agents that operate autonomously and delegate tasks to sub-agents. But because this is a beta with no additional fees, the real test will be reliability and scaling rather than pricing.

FAQ
How much does the Agents API cost?
There are no extra fees beyond token usage. Billing is based solely on token usage.
Where can I run the agents?
Developers can choose between OpenAI-hosted sandboxes or partners like Cloudflare, Vercel, and Oracle.
What can the agents do?
They run for hours, execute code, and process files. The API supports automatic context management, parallel tool use, and delegation to sub-agents.

Get the latest Large Language Models news every morning

For example, today's edition would include:

  • Dynatrace acquires Arize AI as observability shifts to actionSiliconANGLE AI · 4h ago
  • Shared base cuts 100 fine-tunes from 1.5 TB to 19.3 GBDaily Dose of Data Science · 4h ago
  • OpenAI agents hit RubyGems, undisclosed since May 12thSimon Willison's Weblog · 4h ago

AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. Q&As are published on this page for other readers too.

Related Articles

Next articleOvertourism is 'a concentration problem,' Klook's Ethan Lin says