Monday Sep 14
AGENTSOpenAI

OpenAI Makes The Harness Free

14SEP
TOKENS ONLYOPENAIHARNESS

The Agents API puts the Codex harness behind one call: sessions, compaction, subagents, recovery, tools. No harness fee, you pay tokens and sandbox minutes. Run compute on OpenAI, your servers or nine partners.

Public beta since September 10. OpenAI's line: useful agents need a powerful harness that manages context, uses tools efficiently, and coordinates subagents. Versioned access ships with each model launch.

Environments: OpenAI sandbox at container rates, your own infra, or Blaxel, Cloudflare, Daytona, DigitalOcean, E2B, Modal, Oracle, Runloop and Vercel. Self-hosting keeps the data on your box.

Everyone who built a tool loop for Astra last week just watched it become a free line item. Sell the machinery cheap, meter the intelligence.

full brief & sources

⚡ Why this matters

  • The harness was the part every agent team spent months building. OpenAI now runs it for you and charges nothing for it.
  • It moves the margin to tokens and sandbox minutes. Your agent product's cost structure just changed shape.
  • Self-hosted execution is a lock-in release valve. It also tells you where OpenAI thinks the moat is: the model, not the box.

🔍 What happened

  • OpenAI released the Agents API in public beta on September 10, alongside GPT-Live-1 and ChatGPT for Financial Services.
  • One call creates a session with an agent, an environment and a task. OpenAI manages sessions, orchestration, context compaction and recovery. Your app provides tools and picks the execution environment.
  • Capabilities: automatic compaction near the context limit, tool search that loads tool definitions on demand, programmatic tool calling, MCP servers and custom functions, subagents with their own context, resumable sessions, mid-turn steering.
  • Three environments: an OpenAI-hosted sandbox, your own infrastructure via the open-source Codex harness, or partner sandboxes from Blaxel, Cloudflare, Daytona, DigitalOcean, E2B, Modal, Oracle, Runloop and Vercel.
  • Pricing: no fee for the API itself. Model tokens at the model's API rates, OpenAI tools at standard rates, OpenAI sandboxes at container rates. Partner or self-hosted compute bills through the provider.
  • Open questions from developers: US-only data residency and no Zero Data Retention option at launch. Code samples use gpt-6-astra.

💬 Smart takes

  • OpenAI: 'Taking advantage of new model capabilities often means reworking your harness, taking valuable time away from improving your application.'
  • Nitish Garg, CellCog CEO: the harness is now the product, priced at zero. The unit is a session, and a session is not an employee with a role and memory.
  • Skeptic: a free harness that only runs OpenAI models is a free harness with one exit.

🧭 Where this goes

  1. LikelyAnthropic ships an equivalent managed harness on top of Claude Code within weeks.
  2. Likelyagent startups that sold orchestration as the product reprice around memory, permissions and vertical workflows.
  3. Possiblea Zero Data Retention tier and EU residency arrive before general availability.
  4. Possiblethe open-source Codex harness and the managed one drift, and self-hosters get the old version.
  5. Wild Carda partner sandbox becomes the default runtime for most Agents API traffic, not OpenAI's own.

🥄 The Spoon Take

Model prices fell all year. Now the harness price fell to zero. What is left to charge for is the model, the sandbox minutes and the enterprise controls. If your team spent this quarter on compaction and subagent plumbing, stop and read the docs first. Then decide whether your differentiation was ever in the plumbing.

🤔 Pushback

Beta, US residency only, one model family. The free harness is also a very good way to make sure your agents never run on someone else's model.

·OpenAI - Introducing the Agents API·OpenAI docs - Agents API overview·CellCog - OpenAI just made the harness a product