2026年9月10日

Introducing the Agents API

Build and run cloud agents with the Codex harness, fully managed by OpenAI.

載入中…

As we’ve scaled Codex and ChatGPT for Work to millions of people around the world, we’ve learned what it takes to make long-running agents work well in practice. Useful agents need a powerful harness that manages context, uses tools efficiently, and coordinates subagents. They also need infrastructure that keeps them running reliably for days, with environments where they can work with files, run code, and save intermediate results.

Today, we’re introducing the Agents API⁠(在新視窗中開啟) in public beta, bringing that same harness and infrastructure that powers Codex to developers through a simple, flexible API.

What our customers are saying about Agents API

1 之 8

「採用 Agents API 後，我們的評估分數從 0.71 提升至 0.85。API 的子智慧體支援非常出色，大幅加快了我們的工作流程。過去在舊有架構中，觀察及協調子智慧體相當繁瑣；新的 API 則讓延遲縮減為四分之一。我們花了很長時間嘗試最佳化這方面，而內建的子智慧體流程帶來了極大的提升。」

Jack Weissenberger，Ciridae 技術長

「Agents API 讓我們能以不同的思維設計複雜的多步驟工作流程架構。過去，我們必須編寫提示詞鏈並自行管理一組工具呼叫；如今，我們能直接在程式碼中使用智慧體，就像 Codex 在你的筆記型電腦上運作一樣。Agents API 已協助我們解決多項問題，否則我們必須自行建構客製化的智慧體基礎架構。」

Cole Striler，WithCoverage 工程總監

「在 Nash，我們部署了數千個長時間執行的 AI 智慧體，負責管理全球物流網路中數億筆配送作業。OpenAI 的 Agents API 為持續在正式環境中運作的智慧體提供所需的持久工作階段與協調層，負責管理上下文、復原及多步驟執行；Nash 則提供工具與執行環境，讓智慧體能與現實世界連結。因此，我們的智慧體能在歷時數小時甚至數天的複雜工作流程中推理、行動、復原及協作。這些智慧體是正式環境中的基礎架構，為合作夥伴執行關鍵任務物流作業。」

Aziz Alghunaim，Nash.ai 共同創辦人暨技術長

Build cloud agents with a single API call

With the Agents API, you can create a production-ready agent in a single API call by specifying the task, model, tools, and environment:

JavaScript

1import OpenAI from "openai";
2
3const client = new OpenAI();
4
5const session = await client.beta.agents.sessions.create({
6  agent: {
7    model: "gpt-6-astra",
8    tools: [
9      {
10        type: "mcp",
11        server_label: "observability",
12        transport: {
13          type: "http",
14          server_url: "https://observability.example.com/mcp",
15        },
16      },
17    ],
18    multi_agent: { enabled: true, max_concurrent_subagents: 3 },
19  },
20  vault_ids: ["vault_YOUR_VAULT_ID"],
21  environment: {
22    type: "openai_hosted",
23    capability_directories: ["/workspace/capabilities/skills"],
24  },
25  input:
26    "Investigate service-api’s elevated 5xx rate over the last 30 minutes. " +
27    "Delegate deployment, error, and dependency analysis to subagents. " +
28    "Save findings, evidence, and recommended mitigation in /workspace/outputs.",
29});

OpenAI hosts and maintains the harness. You choose the agent’s compute environment: in an OpenAI-managed sandbox, on your own infrastructure, or with one of our sandbox partners. The Agents API gives you a strong foundation for building agents on top of our optimized agent harness and infrastructure, so you can focus on the tools, knowledge, and workflows that make your agent unique.

應用程式將任務傳送至 Agents API，並接收事件與輸出。Agents API 執行代管的 Codex 任務執行框架，將工具呼叫傳送至沙箱，並接收工具結果。應用程式控制自行託管的運算資源。 — Agents API 採用支援 Codex 的同一套任務執行框架與基礎架構，為你的智慧體提供強大功能。

Choose your agent environment

Different workloads need different compute, storage, and deployment options. The Agents API lets you choose a sandbox that fits your application.

We’re partnering with ecosystem providers⁠(在新視窗中開啟), including Blaxel, Cloudflare, Daytona, DigitalOcean, E2B, Modal, Oracle, Runloop, and Vercel, to provide first-class integrations for a range of needs:

Fully managed environments or deployments within your VPC
Specific file and secret storage mechanisms
Different CPU, GPU, and memory configurations, with performance, cold-start, and cost profiles to match your company’s workflow.

沙箱合作夥伴：Modal、Cloudflare、Daytona、Blaxel、Runloop、Vercel、Oracle、E2B 及 DigitalOcean。 — Agents API 提供與熱門生態系供應商的完整整合支援。

OpenAI hosted sandboxes

For developers who want to get started quickly and scale efficiently, we’re also introducing the OpenAI hosted sandbox⁠(在新視窗中開啟). This leverages the same sandboxing infrastructure that powers Codex and ChatGPT.

OpenAI provisions and manages the sandbox, giving your agent a secure and performant environment to run code, work with files, and produce artifacts. These sandboxes can be flexibly configured with your files, packages, skills and plugins to give the agent what it needs to complete the task.

Build with an evolving Codex harness

Taking advantage of new model capabilities often means reworking your harness, taking valuable time away from improving your application. The Agents API provides versioned access to these capabilities with each model launch. We maintain and continuously improve the harness alongside our models, helping your agents get better performance from every upgrade. For example, recent improvements to the harness include:

Keep agents working across long sessions

To support models working for hours, we’ve built context management that helps agents carry relevant information across longer sessions. The Agents API automatically compacts⁠(在新視窗中開啟) earlier context as a session approaches its context limit, preserving information the agent needs to continue. Developers can build workflows that span multiple context windows without implementing their own compaction logic.

Help agents efficiently use more tools

The Agents API helps agents find the right tools and use them efficiently. Tool search⁠(在新視窗中開啟) loads relevant tool definitions as needed, helping reduce token usage and cost while preserving the model’s cache. Once tools are available, programmatic tool calling⁠(在新視窗中開啟) lets agents run calls in parallel, chain related operations, and filter or combine results in code so they can work through large volumes of data while bringing only the relevant results back into context. The Agents API supports MCP, custom functions, and built-in tools like web search.

JSON

1"agent": {
2  "tools": [
3    {
4      "type": "mcp",
5      "server_label": "openai_docs",
6      "transport": {
7        "type": "http",
8        "server_url": "https://developers.openai.com/mcp"
9      }
10    },
11  ]
12}

Let agents parallelize work with subagents

With multi-agent support⁠(在新視窗中開啟), the Agents API can break complex tasks into independent pieces and delegate them to subagents that work in parallel. Each subagent maintains its own context, helping it stay focused on its assignment, while the main agent coordinates their work and brings the results together. This can speed up research, analysis, and coding tasks that benefit from parallel work, without requiring you to build your own orchestration.

JSON

1"agent": {
2  "model": "gpt-6-astra",
3  "multi_agent": {
4    "enabled": true,
5    "max_concurrent_subagents": 3,
6  }
7}

An open-source foundation

The Agents API is powered by the open-source Codex harness, giving developers visibility into the core logic that coordinates model calls, tools, and context. With the Agents API, OpenAI operates and maintains that harness while developers can inspect and learn from its public codebase⁠(在新視窗中開啟).

Start building

Agents API is available in public beta today to all developers. There are no additional fees for using the Agents API – you simply pay for the tokens and tools your agents use, as outlined on our pricing page⁠(在新視窗中開啟).

Explore the Agents API overview⁠(在新視窗中開啟) to learn more, or follow the quickstart⁠(在新視窗中開啟) to get started and bring the harness behind Codex into your own agents.

During the public beta, we’ll iterate quickly based on your feedback as we work toward general availability. Let us know what’s working, where you’re running into friction, and what you need to build and run your agents in production.

作者

OpenAI

繼續閱讀

檢視全部

Now everyone can put data to work

產品2026年9月10日

Introducing ChatGPT for Financial Services

產品2026年9月10日

GPT-Live-1 API | Green-blue cover | Option 038

Build more natural voice experiences with GPT‑Live‑1 in the API

產品2026年9月10日