| 1 | Oct 6, '25 | Introducing AgentKit—build, deploy, and optimize agentic workflows. 💬 ChatKit: Embeddable, customizable chat UI 👷 Agent Builder: WYSIWYG workflow creator 🛤️ Guardrails: Safety s | 46.8× | 3M | 11k | 1.5k | 6.4k |
| 2 | Aug 27, '25 | We’re releasing new Codex features to make it a more effective coding collaborator: - A new IDE extension - Easily move tasks between the cloud and your local environment - Code re | 35.9× | 2.3M | 6.3k | 614 | 2.1k |
| 3 | Apr 9, '24 | GPT-4 Turbo with Vision is now generally available in the API. Vision requests can now also use JSON mode and function calling. Below are some great ways developers are building wi | 28.4× | 1.8M | 2.3k | 416 | 919 |
| 4 | Nov 14, '24 | ChatGPT 🤝 VS Code, Xcode, Terminal, iTerm2 ChatGPT for macOS can now work with apps on your desktop. In this early beta for Plus and Team users, you can let ChatGPT look at coding | 24.8× | 1.6M | 6.8k | 1k | 2.4k |
| 5 | May 8, '25 | You can now connect GitHub repos to deep research in ChatGPT. 🐙 Ask a question and the deep research agent will read and search the repo’s source code and PRs, returning a detaile | 23.5× | 1.5M | 7.9k | 896 | 3.1k |
| 6 | Mar 6, '25 | ChatGPT for macOS can now edit code directly in IDEs. Available to Plus, Pro, and Team users. | 22.3× | 1.4M | 4.9k | 555 | 2k |
| 7 | Jun 3, '25 | We’re rolling out a few updates to Codex today: 1. Codex is rolling out to ChatGPT Plus users today. It includes generous usage limits for a limited time, but during periods of hig | 20.4× | 1.3M | 2.3k | 264 | 593 |
| 8 | Jul 18, '24 | Introducing GPT-4o mini! It’s our most intelligent and affordable small model, available today in the API. GPT-4o mini is significantly smarter and cheaper than GPT-3.5 Turbo. | 20.3× | 1.3M | 2.5k | 559 | 403 |
| 9 | May 19, '25 | 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 | 19.9× | 1.3M | 4.1k | 395 | 1.2k |
| 10 | Apr 23, '25 | Image gen is now available in the API! We’re launching gpt-image-1, making ChatGPT’s powerful image generation capabilities available to developers worldwide starting today. ✅ More | 19.6× | 1.3M | 4.5k | 668 | 1.8k |
| 11 | Mar 20, '25 | Three new state-of-the-art audio models in the API: 🗣️ Two speech-to-text models—outperforming Whisper 💬 A new TTS model—you can instruct it *how* to speak 🤖 And the Agents SDK | 19× | 1.2M | 3.1k | 500 | 1.5k |
| 12 | Oct 30, '25 | You’ve asked for more flexible ways to get more Codex usage: Introducing credits for Codex on ChatGPT Plus and Pro. Credits give you more usage beyond what’s included in your plan, | 17.9× | 1.2M | 1.6k | 132 | 263 |
| 13 | Dec 14, '23 | print("Hello world!") | 16.9× | 1.1M | 3k | 256 | 179 |
| 14 | Sep 10, '25 | We’ve (finally) added full support for MCP tools in ChatGPT. In developer mode, developers can create connectors and use them in chat for write actions (not just search/fetch). Upd | 16.1× | 1M | 5k | 715 | 2.2k |
| 15 | Oct 3, '24 | Introducing canvas—your coding surface in ChatGPT. ✏️ Edit code inline 🐛 Review code and fix bugs 💬 Add logs and comments 🚢 Port to different languages We’ll be adding more to c | 14.6× | 935k | 4.8k | 637 | 1.8k |
| 16 | Jan 24, '25 | ChatGPT with canvas now works with OpenAI o1—and can render HTML and React. | 14.5× | 928k | 3.5k | 408 | 1.5k |
| 17 | Jul 23, '24 | Customize GPT-4o mini for your application with fine-tuning. Available today to tier 4 and 5 users, we plan to gradually expand access to all tiers. First 2M training tokens a day | 14.4× | 922k | 1.6k | 289 | 794 |
| 18 | Aug 6, '24 | Introducing Structured Outputs in the API—model outputs now adhere to developer-supplied JSON Schemas. | 14.3× | 916k | 2.1k | 268 | 706 |
| 19 | Oct 17, '24 | 🔊 The Chat Completions API supports audio now. Pass text or audio inputs, then receive responses in text, audio, or both. | 13.7× | 880k | 1.9k | 280 | 781 |
| 20 | Apr 17, '24 | Introducing a series of updates to the Assistants API 🧵 With the new file search tool, you can quickly integrate knowledge retrieval, now allowing up to 10,000 files per assistant | 12.9× | 826k | 1.7k | 360 | 869 |
| 21 | Sep 13, '24 | We’re hosting an AMA for developers from 10–11 AM PT today. Reply to this thread with any questions and the OpenAI o1 team will answer as many as they can. | 12.7× | 813k | 1.3k | 114 | 329 |
| 22 | Feb 13, '25 | As some of you have noticed, avoid “boomer prompts” with o-series models. Instead, be simple and direct, with specific guidelines. Delimiters (xml tags) will help keep things clean | 12.5× | 804k | 1.5k | 118 | 1.9k |
| 23 | Feb 13, '25 | We’ve put together some best practices on using our o-series models: 🤔 Differences between our reasoning and non-reasoning models 💡 When to use reasoning models 💬 How to approac | 12.3× | 791k | 3.6k | 313 | 3.6k |
| 24 | Mar 11, '25 | We're launching new tools to help developers build reliable and powerful AI agents. 🤖🔧 Timestamps: 01:54 Web search 02:41 File search 03:22 Computer use 04:07 Responses API 10:17 | 12.3× | 789k | 4.8k | 835 | 3.3k |
| 25 | Apr 15, '25 | gpt-4.1 is for developers: | 11.7× | 748k | 5.2k | 285 | 881 |
| 26 | Apr 15, '24 | Introducing the Batch API: save costs and get higher rate limits on async tasks (such as summarization, translation, and image classification). Just upload a file of bulk requests, | 10.8× | 695k | 2.3k | 330 | 782 |
| 27 | May 8, '25 | Remember reinforcement fine-tuning? We’ve been working away at it since last December, and it’s available today with OpenAI o4-mini! RFT uses chain-of-thought reasoning and task-sp | 10.4× | 668k | 2k | 247 | 1.5k |
| 28 | Apr 16, '25 | Meet Codex CLI—an open-source local coding agent that turns natural language into working code. Tell Codex CLI what to build, fix, or explain, then watch it bring your ideas to lif | 10× | 643k | 3k | 447 | 1.5k |
| 29 | Apr 14, '25 | Announcing GPT-4.1, GPT-4.1 mini, and GPT-4.1 nano in the API. TL;DR: Major improvements on coding, instruction following, and long context. 💥 00:00 Intro 02:18 Coding 04:53 Instr | 9.4× | 604k | 2.4k | 444 | 611 |
| 30 | Apr 9, '25 | Announcing @OpenAI Pioneers, a new program for ambitious companies building with our API. Selected teams will partner closely with us on domain-specific evals and custom fine-tuned | 9.4× | 600k | 1.5k | 136 | 703 |
| 31 | Nov 4, '24 | Introducing Predicted Outputs—dramatically decrease latency for gpt-4o and gpt-4o-mini by providing a reference string. Speed up: - Updating a blog post in a doc - Iterating on pri | 9.1× | 582k | 2.5k | 332 | 1.2k |
| 32 | Aug 29, '25 | GPT-5 is now built into Xcode 26! | 8.9× | 569k | 2.3k | 207 | 805 |
| 33 | Aug 28, '25 | The Realtime API is officially out of beta and ready for your production voice agents! We’re also introducing gpt-realtime—our most advanced speech-to-speech model yet—plus new voi | 8.8× | 562k | 2.5k | 369 | 1k |
| 34 | Dec 15, '23 | By popular demand, log probabilities are now in the Chat Completions API! With logprobs for top output tokens, you can build features such as better autocomplete, classification, k | 8.7× | 560k | 1.5k | 187 | 367 |
| 35 | Mar 19, '25 | o1-pro now available in API @benhylak @literallyhimmmm @shl @joshRnold @samgoodwin89 @byamadaro1013 @adonis_singh @alecvxyz @StonkyOli @gabrielchua @UltraRareAF @yukimasakiyu @thee | 8.5× | 544k | 1.4k | 182 | 290 |
| 36 | Jun 26, '25 | Two new additions to the API: 📚 Deep research 🪝 Webhooks | 8.2× | 524k | 2.9k | 236 | 789 |
| 37 | Dec 17, '24 | That’s it. That’s the tweet. The Realtime API now supports WebRTC—you can add Realtime capabilities with just a handful of lines of code. We’ve also cut prices by 60%, added GPT-4o | 8.2× | 524k | 1.3k | 175 | 541 |
| 38 | Oct 1, '24 | Today at DevDay SF, we’re launching a bunch of new capabilities to the OpenAI platform: | 7.9× | 504k | 2.1k | 384 | 651 |
| 39 | Oct 6, '25 | You can start building and testing apps in ChatGPT with the Apps SDK preview, which we're releasing today as an open standard built on MCP. Later this year, we’ll begin accepting a | 7.7× | 497k | 2.5k | 300 | 866 |
| 40 | Aug 7, '25 | We’re also releasing v0.16 of the Codex CLI today. - GPT-5 is now the default model - Use with your ChatGPT plan - A new, refreshed terminal UI `npm i -g @openai/codex` to update | 7.7× | 495k | 2.1k | 355 | 775 |
| 41 | Mar 20, '25 | 🗣️ 00:00 Intro 01:32 Audio agents 03:27 Speech-to-text 06:18 Text-to-speech 08:48 Agents SDK Read more in our blog post: | 7.7× | 494k | 1.9k | 282 | 775 |
| 42 | Mar 26, '25 | MCP 🤝 OpenAI Agents SDK You can now connect your Model Context Protocol servers to Agents: We’re also working on MCP support for the OpenAI API and ChatGPT desktop app—we’ll share | 7.6× | 490k | 3.3k | 596 | 1.2k |
| 43 | Nov 7, '25 | You can now get more Codex usage from your plan and credits with three updates today: 1️⃣ GPT-5-Codex-Mini — a more compact and cost-efficient version of GPT-5-Codex 2️⃣ 50% higher | 7.6× | 489k | 1.8k | 181 | 355 |
| 44 | Jan 25, '24 | Introducing two more model updates: • Updated GPT-4 Turbo preview, completing tasks like code generation more thoroughly and fixes a bug with UTF-8 encoding • New GPT-3.5 Turbo nex | 7.6× | 487k | 1.3k | 196 | 166 |
| 45 | Oct 11, '24 | We announced the Realtime API last week at DevDay SF. It's been amazing to see its adoption—here are some of the coolest examples we’ve seen so far. Let us know if we missed any in | 7.6× | 487k | 2k | 203 | 1.7k |
| 46 | Jan 17, '25 | We’ve put together a reference implementation for building and orchestrating agentic patterns using the Realtime API. You can use this repo to prototype a voice app using multi-age | 7.6× | 485k | 4.5k | 580 | 5.2k |
| 47 | Oct 6, '25 | GPT-5 Pro is now available in the API. It spends more time thinking, for your hardest tasks. | 7.4× | 476k | 1.9k | 162 | 213 |
| 48 | Jan 31, '25 | OpenAI o3-mini is now available in the API for developers on tiers 3–5. It comes with a raft of developer features: ⚙️ Function calling 📝 Developer messages 🗂️ Structured Outputs | 7.4× | 474k | 2.6k | 325 | 436 |
| 49 | May 16, '25 | 00:00 Introducing Codex 01:38 Setup and kicking off tasks 05:05 Environments 07:20 Guiding Codex with a Markdown file 12:00 The Codex origin story 14:25 Verifying and reviewing Cod | 7.3× | 470k | 5.9k | 896 | 8.5k |
| 50 | Jun 13, '25 | Codex can now generate multiple responses simultaneously for a single task, helping you quickly explore possible solutions and pick the best approach. Best-of-N is rolling out to P | 7.2× | 463k | 1.7k | 181 | 697 |
| 51 | Jul 16, '25 | We've improved image generation in the API. Editing with faces, logos, and fine-grained details is now much higher fidelity with features preserved. 🔍 Edit specific objects, creat | 7.2× | 460k | 2.1k | 241 | 1k |
| 52 | May 1, '24 | We’ve open sourced a new quickstart to help you build with the Assistants API and @nextjs. It comes with sample code for creating a chat interface with streaming, and using tools l | 7.1× | 458k | 1.5k | 238 | 943 |
| 53 | May 27, '25 | Watch o3 play Pokémon—live. See how it plans its next move, explains its reasoning, analyzes the map visually, and saves to memory. Thank you community member @Clad3815 for putting | 7.1× | 455k | 1.7k | 233 | 421 |
| 54 | Aug 7, '25 | GPT-5 is now playing Pokémon. Watch the Twitch stream below — and open the companion site to see its agent data in real time: prompts, reasoning, tools, self-critique, and more. | 7.0× | 446k | 2.4k | 230 | 456 |
| 55 | Feb 16, '24 | We’ve just doubled GPT-4 Turbo rate limits across the board and removed all daily limits. Here are the new maximum tokens per minute (TPM) you can now achieve. | 6.9× | 440k | 1.8k | 205 | 192 |
| 56 | May 21, '25 | Introducing support for remote MCP servers, image generation, Code Interpreter, and more in the Responses API. | 6.8× | 435k | 2.2k | 247 | 967 |
| 57 | May 16, '25 | Here’s how to get started with Codex: | 6.7× | 428k | 1.7k | 247 | 1.2k |
| 58 | Sep 29, '25 | We’re introducing the Agentic Commerce Protocol, an open standard co-developed with @Stripe that enables programmatic commerce flows between users, AI agents, and businesses. | 6.4× | 408k | 2k | 245 | 610 |
| 59 | May 13, '24 | GPT-4o is now available in the API. It’s as smart as GPT-4 Turbo, has improved vision capabilities, and is much more efficient—2x faster, 50% cheaper, 5x rate limits. It supports t | 6.3× | 404k | 1.9k | 331 | 281 |
| 60 | Nov 13, '25 | We got feedback on GPT‑5.1 from a handful of companies and developers. Here are their early impressions: | 6.1× | 389k | 1.6k | 60 | 387 |
| 61 | Jun 10, '25 | We’re cutting the price of o3 by 80% and introducing o3-pro in the API, which uses even more compute. o3: Input: $2 / 1M tokens Output: $8 / 1M tokens Now in effect. We optimized o | 6.0× | 383k | 1.5k | 190 | 245 |
| 62 | Feb 27, '25 | GPT-4.5 with @flavioAd’s prompt. Then we asked to make it more creative. | 5.4× | 348k | 2k | 157 | 362 |
| 63 | Aug 21, '25 | Two big updates to the Responses API today. 🖇️ Connectors — Pull context from Gmail, Google Calendar, Dropbox, and more in a single API call. 💬 Conversations — Persist chat threa | 5.3× | 342k | 1.9k | 194 | 867 |
| 64 | Sep 23, '25 | GPT-5-Codex is live in the Responses API. If you use the Codex CLI via API key, you can now also use GPT-5-Codex. | 5.3× | 338k | 1.3k | 118 | 211 |
| 65 | Sep 18, '24 | Just 5x'd rate limits again: o1-preview: 500 requests per minute o1-mini: 1000 requests per minute | 5.1× | 325k | 1.6k | 136 | 129 |
| 66 | Jun 3, '25 | 🆕 Four updates to building agents with OpenAI: Agents SDK in TypeScript, a new RealtimeAgent feature for voice agents, Traces support for the Realtime API, and improvements to our | 5.0× | 319k | 1.5k | 125 | 701 |
| 67 | Aug 15, '25 | Six tips for coding with GPT-5: | 4.9× | 317k | 2.5k | 295 | 2.6k |
| 68 | Aug 5, '24 | We’re taking OpenAI DevDay on the road! Join us this fall in San Francisco, London, or Singapore for hands-on sessions, demos, and best practices. Meet our engineers and see how de | 4.9× | 317k | 1.1k | 148 | 143 |
| 69 | Aug 7, '25 | Here’s a megathread of GPT-5 already at work: | 4.9× | 314k | 1.6k | 109 | 964 |
| 70 | Sep 15, '25 | Xcode 26 is now available on the Mac App Store. Sign in with your ChatGPT account and code with GPT-5 built-in. | 4.8× | 310k | 2.2k | 188 | 581 |
| 71 | May 14, '25 | Coded up by GPT-4.1, rolling out today in ChatGPT. | 4.8× | 306k | 2.1k | 149 | 331 |
| 72 | Apr 8, '25 | Introducing the Evals API. You can now programmatically define tests, automate evaluation runs, and quickly iterate on prompts. Evals are still available in the dashboard—and now t | 4.7× | 303k | 2k | 208 | 1.1k |
| 73 | Jun 4, '25 | How to set up a remote MCP server and connect it to ChatGPT deep research: | 4.6× | 297k | 2k | 261 | 2.2k |
| 74 | Aug 7, '24 | Our newest GPT-4o model is 50% cheaper for input tokens and 33% cheaper for output tokens. It also supports Structured Outputs, which ensures model outputs exactly match your JSON | 4.4× | 283k | 1.5k | 193 | 261 |
| 75 | Apr 14, '25 | quasar /ˈkweɪ.zɑːr/ noun A very energetic and distant active galactic nucleus, powered by a supermassive black hole that emits exceptionally large amounts of energy across the elec | 4.4× | 283k | 1.7k | 105 | 170 |
| 76 | Sep 12, '25 | gpt-5 and gpt-5-mini API rate limits are now more than doubled for these tiers: gpt-5 Tier 1: 30K → 500K TPM (1.5M batch) Tier 2: 450K → 1M (3M batch) Tier 3: 800K → 2M Tier 4: 2M | 4.3× | 275k | 2.6k | 188 | 288 |
| 77 | May 21, '25 | The OpenAI Responses API now supports Model Context Protocol. 📡 You can connect our models to any remote MCP server with just a few lines of code. | 4.1× | 263k | 1.3k | 178 | 551 |
| 78 | Nov 18, '24 | Streaming is now available for OpenAI o1-preview and o1-mini. 🌊 And we’ve opened up access to these models for developers on all paid usage tiers. | 4.1× | 263k | 1.9k | 212 | 320 |
| 79 | Aug 19, '25 | is quickly becoming a popular way to share instructions with coding agents in your repo. Now supported in Cursor, Amp, Jules, Factory, RooCode, and Codex. | 4.1× | 261k | 1.6k | 150 | 940 |
| 80 | Aug 5, '25 | 🧑💻 Open Model Hackathon 🧑💻 @huggingface, @nvidia, @ollama, @vllm_project, and @OpenAIDevs challenge you to build something weird, useful, or groundbreaking (or all three!) wi | 4.0× | 259k | 1.5k | 144 | 453 |
| 81 | Sep 15, '25 | $ npm i -g @openai/codex $ codex -m gpt-5-codex | 4.0× | 257k | 2.3k | 234 | 897 |
| 82 | Feb 6, '25 | Canvas sharing is now live in ChatGPT. Share your canvas with others—they can view, interact with, or edit to make it their own. 🧑🎨 | 3.9× | 252k | 1.6k | 188 | 361 |
| 83 | Oct 30, '24 | Two Realtime API updates: - You can now build speech-to-speech experiences with five new voices—which are much more expressive and steerable. 🤣🤫🤪 - We're lowering the price by u | 3.8× | 244k | 1.7k | 205 | 595 |
| 84 | Aug 13, '25 | GPT-5 Startup Hackathon with @cerebral_valley We gave startups 24 hours to build with GPT-5. Over 275 builders flew in from around the world to hack with our team and @kevinweil. � | 3.7× | 234k | 1.3k | 91 | 490 |
| 85 | Mar 11, '25 | Introducing web search in the OpenAI API—get fast, up-to-date answers with links to relevant web sources. Powered by the same model used for ChatGPT search. 🔎🌐 Available to all d | 3.4× | 220k | 1.6k | 152 | 483 |
| 86 | Nov 20, '24 | This new GPT-4o snapshot is now available in the API as `gpt-4o-2024-11-20`: . | 3.2× | 208k | 1.4k | 150 | 220 |
| 87 | Oct 17, '24 | A lot of you have asked for diffs in ChatGPT with canvas. It's now live! Hit "show changes" to see what's changed in your code. | 3.1× | 199k | 1.4k | 133 | 213 |
| 88 | Mar 27, '25 | `chatgpt-4o-latest` is now updated in the API, but stay tuned—we plan to bring these improvements to a dated model in the API in the coming weeks. | 3.0× | 195k | 1.3k | 112 | 147 |
| 89 | Jun 16, '25 | 🇵 🇷 🇴 🇲 🇵 🇹 🇸 are an API primitive now! Centrally manage, version, and optimize prompts. Use (and reuse!) prompts across the Playground, API, Evals, and Stored Completions. | 3.0× | 194k | 1.8k | 148 | 957 |
| 90 | Sep 16, '25 | We trained gpt-5-codex to be great at both responsive and mobile front-ends. Here's a thread of some examples: "Make a pixel art game where I can walk around and talk to other vill | 3.0× | 191k | 1.8k | 174 | 749 |
| 91 | Jun 26, '25 | Web search is now available with OpenAI o3, o3-pro, and o4-mini. The model can search the web within its chain-of-thought! 🧠🌐 $10 / 1K tool calls | 3.0× | 190k | 1.9k | 186 | 556 |
| 92 | Mar 18, '25 | You can now input PDF files directly to the Responses and Chat Completions APIs! Then let o1, gpt-4o, or gpt-4o-mini generate text with that context. | 2.5× | 160k | 1.4k | 178 | 574 |
| 93 | Sep 9, '25 | You can now use Codex CLI to quickly upgrade from Chat Completions to Responses! This toolkit: • Finds legacy usage in your repo • Proposes and applies edits • Updates import/reque | 2.5× | 159k | 1.5k | 114 | 515 |
| 94 | Sep 24, '24 | Updates to OpenAI o1 API availability: - We’ve expanded access to developers on tier 4 (100 requests per minute for both models). - We’ve 5x’d rate limits for developers on tier 5 | 2.4× | 152k | 1.3k | 135 | 102 |
| 95 | Jul 10, '25 | To use a PDF with the OpenAI API, you can just pass its URL now—no upload needed! 📄🔗 | 2.1× | 133k | 1.5k | 111 | 567 |
| 96 | Sep 26, '25 | We've updated function calling to support files and images as tool call outputs. You can now call functions like `generate_chart` or `load_image` and return those files back to the | 2.1× | 133k | 1.5k | 148 | 480 |
| 97 | Mar 5, '25 | OpenAI o1 and o3-mini are now available in the API for developers on all paid usage tiers. Use them with: 🌊 Streaming ⚙️ Function calling 🗂️ Structured Outputs 🧠 Reasoning effor | 2.1× | 133k | 1.4k | 137 | 239 |
| 98 | Jul 11, '25 | We've raised Structured Outputs limits to support larger schemas: Object properties: from 100 → 5,000 Characters in string: 15,000 → 120,000 Enum values: 500 → 1,000 Total characte | 1.9× | 119k | 1.3k | 88 | 250 |
| 99 | Mar 7, '25 | We've made a new models page in our docs—you can now easily see a breakdown of each model's capabilities and compare models side-by-side. | 1.8× | 116k | 1.4k | 146 | 359 |
| 100 | Jan 17, '25 | Our new guide to function calling can help you write clearer functions—and we've loaded it up with best practices and working examples: . | 1.8× | 115k | 1.4k | 171 | 1.2k |
| 101 | Oct 16 | Building apps with GPT-Live-1? Give them a voice that fits. Here’s how to shape a voice with a prompt or choose from new international preset voices: | 0.5× | 32k | 615 | 36 | 173 |
@karpathy
@levelsio
@paulg
@naval
@marclou
@illyism