GenAIWiki
Developer tool

OpenAI Agents API Verified

The OpenAI Agents API is the September 10, 2026 public-beta API that exposes the Codex harness as a managed cloud runtime. OpenAI runs sessions, orchestration, context compaction, and recovery. Your application supplies tools and chooses the environment: an OpenAI-hosted sandbox or a self-hosted executor. Agents can run commands, edit files, call MCP servers, spawn subagents, and resume durable sessions. Requests use the OpenAI-Beta: agents=v1 header. This is not the Codex CLI product and not the in-process Agents SDK.
API availableNo extra Agents API fee; pay selected model token rates, built-in tool rates, and OpenAI-hosted sandbox container ratesopenaiagentsapicodexsandboxmcp
FeaturedUpdated todayLast verified: September 2026

Key insights

Concrete technical or product signals.

  • Use Agents API when you want OpenAI to run the Codex loop. Use Codex when you want the first-party coding product. Use the Agents SDK when the loop stays in your process.
  • Official docs say US data residency only and no Zero Data Retention. A self-hosted sandbox does not make the API ZDR-eligible.

Use cases

Where this shines in production.

  • Long-running cloud agents with durable sessions
  • Hosted-sandbox coding and investigation agents
  • MCP-connected workplace or docs agents

Limitations & trade-offs

What to watch for.

  • Public beta. The interface is not frozen.
  • API keys need api.agents.read, api.agents.write, and api.responses.write for the documented quickstart.
  • Function-tool handlers that go offline can stall a turn waiting for a result.

Models referenced

Declared model dependencies or integrations.

GPT-6 Astra, selectable OpenAI API models

Related prompts

Hand-picked or latest prompt templates.

Looking for a tighter match? Search the prompt library.

OpenAI Agents API FAQ

What is OpenAI Agents API?

The OpenAI Agents API is the September 10, 2026 public-beta API that exposes the Codex harness as a managed cloud runtime. OpenAI runs sessions, orchestration, context compaction, and recovery. Your application supplies tools and chooses the environment: an OpenAI-hosted sandbox or a self-hosted executor. Agents can r...

When should teams use OpenAI Agents API?

Long-running cloud agents with durable sessions

What should teams watch out for with OpenAI Agents API?

Public beta. The interface is not frozen.

Related

Comparisons, platforms, and models teams often view next.

This page is based on publicly available documentation, benchmarks, and real-world usage patterns. Last reviewed for accuracy recently.