OpenAI Launches the Agents API in Public Beta, Putting the Codex Harness Behind One API Call
OpenAI released its Agents API in public beta, exposing the managed Codex harness with hosted or self-hosted sandboxes, MCP tools, and subagents.
The Agents API is a managed service built on the open-source Codex harness, handling context compaction, tool search, programmatic tool calling, and multi-agent orchestration. Agents run in OpenAI-hosted sandboxes, self-hosted environments, or partner sandboxes from Blaxel, Cloudflare, Daytona, DigitalOcean, E2B, Modal, Oracle, Runloop, and Vercel. Data residency is US-only and Zero Data Retention is unsupported. Examples use model gpt-6-astra; vendor-reported results include SafetyKit cutting case review cost 60% and Ciridae achieving 4x lower subagent latency.
- Sessions are durable, resumable, and steerable mid-turn
- Programmatic tool calling runs calls in parallel and filters results in code
- Pricing follows tokens, tools, and container time with no extra fee
- Scalability learnings came from scaling Codex and ChatGPT for Work
- Vendors
- OpenAI
- Products
- Agents APICodex
- Countries
- United States
- AI models
- gpt-6-astra
From the original article
4 min read at marktechpost.com
OpenAI has released the Agents API in public beta. It gives developers the same harness and infrastructure that run Codex. OpenAI hosts and maintains the harness.
By Asif Razzaq · marktechpost.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.