Anmelden
OpenAI Agents API logo

OpenAI Agents API

Beta

OpenAI's managed Codex harness, exposed as an API for long-running agents

Website besuchen
Bedingt

OpenAI's Agents API is the runtime OpenAI itself rates lowest in integration effort of the three it compares: it exposes the managed Codex harness with durable sessions, context compaction, subagents and hosted or partner sandboxes, and charges no fee beyond tokens, tools and container time. Conditional because it is a public beta that currently offers US-only data residency and no Zero Data Retention. Right for product teams already building on the OpenAI API; wrong for workloads that require ZDR or data residency outside the US.

KI-nativ

OpenAI runs the agent loop on its infrastructure: a managed Codex harness drives model calls, tools and sandbox commands in durable sessions

Ist es das Richtige für dich?

Gut für

  • Long-running tasks where OpenAI manages the agent and saves its progress, which is the use OpenAI's runtime comparison assigns to the Agents API
  • Shipping an agent without building the loop: OpenAI handles session orchestration, context compaction and recovery on its own infrastructure
  • Code execution and file work in an OpenAI-hosted sandbox, in your own infrastructure, or with a partner sandbox such as E2B, Modal, Daytona or Vercel
  • Extending agents with your own tools and MCP servers, plus skills loaded from the environment
  • Splitting complex work across subagents, which OpenAI's docs describe as breaking work into subtasks and delegating to subagents
  • Teams already on OpenAI API billing, since OpenAI says there are no additional fees beyond the tokens and tools agents use

Nicht geeignet für

  • Workloads that require Zero Data Retention, which the Agents API currently does not support
  • Data that must stay outside the United States, since data residency is currently supported only in the US
  • Production systems that cannot absorb beta changes: it launched as a public beta and every request requires the OpenAI-Beta: agents=v1 header
  • Keeping the agent loop inside your own application, a use OpenAI's runtime comparison assigns to the Agents SDK, which runs inside your application
  • Budgeting from token prices alone, since OpenAI-hosted sandboxes bill separately at standard container rates

Unsere Erfahrung

We haven't tested OpenAI Agents API ourselves. This profile is based on public documentation, user reviews, and community feedback.

Preise

Kostenpflichtig
Public betaUsage-based, no platform fee
  • Model usage billed at the selected model's API rates
  • OpenAI tools billed at their standard rates
  • OpenAI-hosted sandboxes billed at standard container rates
  • Self-hosted and partner sandboxes supported
Alle Preise ansehen

Workflow-Rezepte

Run a first agent session

Start one agent session in an OpenAI-hosted sandbox following OpenAI's quickstart

  1. Create an application API key in your OpenAI Platform project with api.agents.read, api.agents.write and api.responses.write
  2. Keep the key outside the agent's sandbox and export it as an environment variable
  3. Install the SDK with pip install --upgrade openai or npm install openai
  4. Create a session with an agent configuration, environment type openai_hosted and your input instructions, sending the OpenAI-Beta: agents=v1 header
  5. Stream session events, wait for agent.session.turn.completed, then check the agent's reported execution result
  6. Save the session_id to continue the work, or delete the session when finished

Noch keine Urteilsänderungen

Die Uhr läuft ab dem ersten Tag — Änderungen erscheinen hier, sobald sich unser Urteil weiterentwickelt.

Quellen

Prüfprotokoll

Noch keine Prüfungen

Wir haben für diesen Eintrag noch keine Prüfung erfasst. Sobald eine Prüfung läuft, erscheint ihr Verlauf hier.

Wie wir bewerten

Wollen Sie das in Ihrem Unternehmen laufen haben?

Wir haben dieses Tool getestet und bauen täglich mit Tools wie diesem. Sagen Sie uns den Ablauf, wir richten es ein, integrieren es und übergeben es funktionsfähig.

Sagen Sie uns, was Sie brauchen (wird in einem neuen Tab geöffnet)Sehen Sie, was wir bauen

Das Gespräch läuft auf Gnosari, einem der Tools in diesem Verzeichnis. Ein echtes Gespräch, kein Verkaufsskript.