OpenAI Developers's banner
OpenAI Developers's profile picture

OpenAI Developers

@OpenAIDevs380,538 subscribers

Official updates for developers building with Codex & the OpenAI Platform • Service status: https://t.co/kZwnwdYYEq

Shorts

Review pull requests and make follow-up edits without leaving Codex. PR Chat lets you ask Codex questions about a specific pull request in context. Inline code editing lets you send review feedback to Codex, inspect the proposed patch inline, and edit, accept, or reject it.

Review pull requests and make follow-up edits without leaving Codex. PR Chat lets you ask Codex questions about a specific pull request in context. Inline code editing lets you send review feedback to Codex, inspect the proposed patch inline, and edit, accept, or reject it.

244,256 görüntüleme

Your favorite Codex shortcuts are getting an upgrade. July 15th.

Your favorite Codex shortcuts are getting an upgrade. July 15th.

1,227,740 görüntüleme

Pets. Now in Codex. Use /pet to wake your pet.

Pets. Now in Codex. Use /pet to wake your pet.

3,463,032 görüntüleme

🆕 Codex quality-of-life updates landed this week Starting with long threads: scrolling is smoother now, and your place stays put as you move through the conversation.

🆕 Codex quality-of-life updates landed this week Starting with long threads: scrolling is smoother now, and your place stays put as you move through the conversation.

726,741 görüntüleme

Subagents are now available in Codex. You can accelerate your workflow by spinning up specialized agents to: • Keep your main context window clean • Tackle different parts of a task in parallel • Steer individual agents as work unfolds

Subagents are now available in Codex. You can accelerate your workflow by spinning up specialized agents to: • Keep your main context window clean • Tackle different parts of a task in parallel • Steer individual agents as work unfolds

1,645,639 görüntüleme

Private MCP servers 🤝 OpenAI products Your team can keep MCP servers inside your network while ChatGPT, Codex, and the Responses API connect through outbound-only HTTPS. 🔗

Private MCP servers 🤝 OpenAI products Your team can keep MCP servers inside your network while ChatGPT, Codex, and the Responses API connect through outbound-only HTTPS. 🔗

584,540 görüntüleme

Customize your Codex pet with /hatch

Customize your Codex pet with /hatch

885,467 görüntüleme

Introducing AgentKit—build, deploy, and optimize agentic workflows. 💬 ChatKit: Embeddable, customizable chat UI 👷 Agent Builder: WYSIWYG workflow creator 🛤️ Guardrails: Safety screening for inputs/outputs ⚖️ Evals: Datasets, trace grading, auto-prompt optimization

Introducing AgentKit—build, deploy, and optimize agentic workflows. 💬 ChatKit: Embeddable, customizable chat UI 👷 Agent Builder: WYSIWYG workflow creator 🛤️ Guardrails: Safety screening for inputs/outputs ⚖️ Evals: Datasets, trace grading, auto-prompt optimization

2,992,802 görüntüleme

Your Codex activity now has a home, and an easier way to share it. Codex profiles show your activity graph, streaks, lifetime tokens, peak daily tokens, and top features like plugins and /fast mode. Private by default. Share a card when you want to.

Your Codex activity now has a home, and an easier way to share it. Codex profiles show your activity graph, streaks, lifetime tokens, peak daily tokens, and top features like plugins and /fast mode. Private by default. Share a card when you want to.

330,633 görüntüleme

“If you’re a builder, what a time to be alive.” Peter Steinberger 🦞 breaks down how his workflow changed when you can just build things covering how he prompts, iterates, and ships with Codex. Full episode drops 2/23.

“If you’re a builder, what a time to be alive.” Peter Steinberger 🦞 breaks down how his workflow changed when you can just build things covering how he prompts, iterates, and ships with Codex. Full episode drops 2/23.

858,423 görüntüleme

Ask our developer docs. They’ll show you the way The new docs agent on 🔗 helps you find answers about OpenAI products and takes you directly to the relevant documentation.

Ask our developer docs. They’ll show you the way The new docs agent on 🔗 helps you find answers about OpenAI products and takes you directly to the relevant documentation.

187,171 görüntüleme

GPT-5.4 can write Playwright code, read screenshots, and issue keyboard/mouse actions to operate computers. You can steer its behavior and set custom confirmation policies for different risk tolerances. On OSWorld-Verified, it achieves a state-of-the-art 75.0% success rate.

GPT-5.4 can write Playwright code, read screenshots, and issue keyboard/mouse actions to operate computers. You can steer its behavior and set custom confirmation policies for different risk tolerances. On OSWorld-Verified, it achieves a state-of-the-art 75.0% success rate.

558,742 görüntüleme

2 quality-of-life improvements for developers working with Codex today: Codex background agents now have stable pixel identicons. When the same agent shows up across tabs, mentions, transcripts, and the thread panel, it’s easier to recognize at a glance.

2 quality-of-life improvements for developers working with Codex today: Codex background agents now have stable pixel identicons. When the same agent shows up across tabs, mentions, transcripts, and the thread panel, it’s easier to recognize at a glance.

173,445 görüntüleme

Codex is now available in the ChatGPT iOS app! Start new tasks, view diffs, ask for changes, and even push PRs—all on the go. And you can keep tabs on Codex with live activities on your lock screen, or pick things up again when you're back at your computer. 🏃🤳

Codex is now available in the ChatGPT iOS app! Start new tasks, view diffs, ask for changes, and even push PRs—all on the go. And you can keep tabs on Codex with live activities on your lock screen, or pick things up again when you're back at your computer. 🏃🤳

1,275,107 görüntüleme

Bring Codex to your team without fixed seat costs. We’re rolling out usage-based pricing for Codex in ChatGPT Business and Enterprise plans, so teams have a more flexible way to get started.

Bring Codex to your team without fixed seat costs. We’re rolling out usage-based pricing for Codex in ChatGPT Business and Enterprise plans, so teams have a more flexible way to get started.

262,372 görüntüleme

You can ask Codex to update an existing repo to GPT-5.5.

You can ask Codex to update an existing repo to GPT-5.5.

185,639 görüntüleme

Shipped papercut: new diff markers setting in Appearance. Prefer classic + / - markers when reviewing diffs? You can now use those instead of only color-coded diff bars. Default stays the same unless you opt in.

Shipped papercut: new diff markers setting in Appearance. Prefer classic + / - markers when reviewing diffs? You can now use those instead of only color-coded diff bars. Default stays the same unless you opt in.

103,324 görüntüleme

🔊 The Chat Completions API supports audio now. Pass text or audio inputs, then receive responses in text, audio, or both.

🔊 The Chat Completions API supports audio now. Pass text or audio inputs, then receive responses in text, audio, or both.

877,647 görüntüleme

We updated Settings search and navigation. • Search covers more controls • Appearance controls and host filtering are clearer • Custom-provider settings are easier to find • Pets has its own panel

We updated Settings search and navigation. • Search covers more controls • Appearance controls and host filtering are clearer • Custom-provider settings are easier to find • Pets has its own panel

37,156 görüntüleme

o1-pro now available in API ben hylak him Sahil Lavingia sam Kai adi Alec Velikanov olives Zoe MK@LLM Researcher @theemao christian It uses more compute than o1 to provide consistently better responses. Available to select developers on tiers 1–5. Supports vision, function calling, Structured Outputs, and works with the Responses and Batch APIs. With more compute, comes more cost: $150 / 1M input tokens and $600 / 1M output tokens.

o1-pro now available in API ben hylak him Sahil Lavingia sam Kai adi Alec Velikanov olives Zoe MK@LLM Researcher @theemao christian It uses more compute than o1 to provide consistently better responses. Available to select developers on tiers 1–5. Supports vision, function calling, Structured Outputs, and works with the Responses and Batch APIs. With more compute, comes more cost: $150 / 1M input tokens and $600 / 1M output tokens.

543,456 görüntüleme

Videos