OpenAI Dev Day 2025: Everything Announced

Last updated: June 11, 2026

Apps Within ChatGPT#

OpenAI is turning ChatGPT into a hub. The new Apps feature lets you access external services directly inside conversations. No context switching. No copy-paste workflows.

For model-selection context, compare this with OpenAI Codex: Cloud AI Coding With GPT-5.3 and Codex vs Claude Code in April 2026: Which Agent for Which Job; model quality matters most when it is tied to a concrete coding workflow.

Want a Spotify playlist? ChatGPT generates it and creates it directly in your account. House hunting? Query Zillow and browse listings without leaving the chat. The initial partners include Canva, Expedia, and several others, but the pattern is clear: OpenAI wants ChatGPT to be the interface for the web.

Agent Kit: Visual Agent Building#

The biggest announcement is Agent Kit. Think n8n or Zapier, but purpose-built for AI agents. It is a no-code platform for building agent workflows.

You still need to design the logic. Conditional branches, tool selection, and orchestration all require thought. But the interface removes the boilerplate. You can wire together file search, MCP integrations, and custom agents through a visual canvas. Route conversations down different paths based on user intent. Add tools where needed.

For developers who have been duct-taping agent frameworks together, this consolidates the stack.

Sora 2 Hits the API#

Video generation is now programmable. Sora 2 and Sora 2 Pro are available via API, opening the door to automated video pipelines.

The integration is straightforward: select your model, pass a prompt, submit the request, and poll for completion. Video generation takes time, so plan for asynchronous workflows. But the customization options, model selection, and prompt control mean you can build video features directly into products rather than treating generation as a manual step.

Codex: Slack, SDK, and Analytics#

Codex received three meaningful updates. First, you can now access the agent directly within Slack. Second, the Codex SDK lets you build custom agents on top of OpenAI's infrastructure. If you want to create your own lovable-style app builder or specialized coding assistant, the SDK provides the foundation. Third, usage analytics are now available so you can track how your agents consume tokens and where costs accumulate.

GPT-5 Pro Enters the API#

The flagship model is here, but it comes with flagship pricing. GPT-5 Pro costs $15 per million input tokens and $120 per million output tokens. The context window is massive: 400,000 tokens in, 272,000 tokens out.

Independent benchmarks were not available at announcement time, but the expectation is clear. At this price point, OpenAI is positioning it as the best model available across reasoning, coding, and complex task completion. Whether it holds that position depends on head-to-head testing against competitors, but the specs suggest top-tier performance.

Realtime Mini and Image Mini#

Two new cost-optimized models launched alongside the premium tier.

GPT Realtime Mini delivers the same voice capabilities as the standard real-time API, intonation and tone understanding included, at 70% lower cost. For voice applications, this makes OpenAI competitive on price without sacrificing the conversational quality that distinguishes their audio models.

GPT Image 1 Mini offers the same deal for visuals. The model handles everything from infographics to photorealistic images at a reduced price point compared to the full GPT Image 1.

Widgets and Conditional UI#

The Agent Kit demo revealed a subtle but powerful feature: conditional widgets. Agents can trigger custom UI elements based on conversation state.

Ask about flights, meet the right criteria, and the agent renders a formatted card instead of plain text. You define the widget structure, styling, and rendering logic within the builder. This moves beyond text-only responses into structured, interactive outputs without leaving the ChatGPT ecosystem.

---

Official Sources#

---

FAQ#

What is OpenAI Agent Kit?#

Agent Kit is OpenAI's no-code visual builder for AI agent workflows. It works like n8n or Zapier but is purpose-built for AI agents. You can wire together file search, MCP integrations, and custom agents through a visual canvas, route conversations based on user intent, and add tools where needed - all without writing code.

What is the ChatGPT Apps feature?#

ChatGPT Apps lets you access external services directly inside ChatGPT conversations. Initial partners include Spotify, Zillow, Canva, and Expedia. You can generate a Spotify playlist and have it created in your account, or browse Zillow listings, all without leaving the chat interface.

How much does GPT-5 Pro cost?#

GPT-5 Pro costs $15 per million input tokens and $120 per million output tokens. The context window supports 400,000 input tokens and 272,000 output tokens. This positions it as OpenAI's flagship model for reasoning, coding, and complex task completion.

Is Sora 2 available via API?#

Yes. Sora 2 and Sora 2 Pro are both available via API for programmatic video generation. You select your model, pass a prompt, submit the request, and poll for completion. Video generation is asynchronous, so plan for polling workflows.

What are the new Codex features from Dev Day?#

Codex received three updates: Slack integration for accessing the agent directly in Slack workspaces, a Codex SDK for building custom agents on OpenAI infrastructure, and usage analytics for tracking token consumption and cost accumulation across your agents.

What are GPT Realtime Mini and GPT Image 1 Mini?#

These are cost-optimized versions of OpenAI's voice and image models. GPT Realtime Mini delivers the same voice capabilities (including intonation and tone understanding) at 70% lower cost. GPT Image 1 Mini handles infographics and photorealistic images at reduced pricing compared to the full model.

What are Agent Kit widgets?#

Agent Kit supports conditional widgets - custom UI elements that agents can trigger based on conversation state. When specific criteria are met (like asking about flights), the agent renders a formatted card instead of plain text. You define widget structure, styling, and rendering logic within the visual builder.

How does Agent Kit compare to other agent frameworks?#

Agent Kit consolidates what developers previously achieved by combining multiple frameworks like LangChain, CrewAI, or custom orchestration code. It provides a visual interface for agent logic, tool selection, and conditional routing, removing boilerplate while still requiring you to design the underlying logic.

---

Watch the Video#

Continue Reading#

• OpenAI's GPT 5.4 in 10 Minutes