Official updates for developers building with Codex & the OpenAI Platform • Service status: status.openai.com
- Tweets 2,815
- Following 1
- Followers 448,406
- Likes 4,418
Heard you liked the @modretro Chromatic.
So we added one to the side quest.
You have 48 more hours to join.
side-quests.openai.chatgpt.s…
Ready for a DevDay side quest?
10 builder challenges.
5 Codex Micros up for grabs.
Complete any 5 side quests to earn 1 raffle ticket for each.
48 hours. Join from anywhere 🌎
67
48
767
185,801
Shareable profiles bring your Sites and plugins together in ChatGPT, so others can find and reuse what you’ve made.
Built it? Show it off.
85
53
1,148
89,367
Plugin extensions let you build interactive panels, file viewers, and a sidebar home in ChatGPT.
Get clearer feedback when submitting your plugin for review.
With support for the proposed MCP Events specification, events in connected apps can start automations in ChatGPT:
developers.openai.com/plugin…
8
20
261
170,408
Open a pull request in the ChatGPT Work or Codex desktop app, inspect the diff, and ask Codex about the changes.
You can also get feedback on your own changes before sharing them:
learn.chatgpt.com/docs/code-…
3
1
57
10,656
Ready for a DevDay side quest?
10 builder challenges.
5 Codex Micros up for grabs.
Complete any 5 side quests to earn 1 raffle ticket for each.
48 hours. Join from anywhere 🌎
61
83
1,005
328,871
Give your app real-time decision-making with Decisions API, powered by GPT-6 Luna.
Define questions and possible answers to classify content, route requests, or choose an agent’s next action.
Available in limited preview.
233
417
5,921
741,979
There’s a lot more for builders packed into the Codex CLI update:
– /usage for activity and usage analytics
– New themes to choose from with /theme
– Support for managed worktrees
– Mermaid diagrams and LaTeX rendered directly in the terminal
– Collapsible diffs and tool output
– Dedicated areas for status, hints, and keyboard shortcuts
1
4
100
14,856
You can now talk to Codex in your terminal. And it talks back.
Use /voice to kick off work or talk through your next step, then jump into Agents to see everything moving.
6
6
97
7,135
The Codex CLI now gives you a better way to manage parallel work.
Use /agents to see what’s running, check progress, and jump between tasks.
Want to try another direction? /fork a conversation into a worktree with the same context and a separate checkout.
5
11
157
13,427
Older history loads as you scroll, beyond your terminal’s scrollback limit.
Your composer stays pinned and ready for your next message, so you can explore long sessions without scrolling back to type.
3
6
177
19,211
Codex CLI just got a major refresh, with a new look and powerful new capabilities.
We’re continuing to invest in Codex CLI for developers who live in the command line.
New full-screen interface, better readability, and ways to manage parallel work, all inside your terminal.
104
186
4,123
252,256
Codex cloud environments are rolling out to Plus, Pro, Business, and Enterprise.
In Business and Enterprise workspaces, you can share environments so your whole team can work from the same setup.
Just select a cloud environment when you start a task, wherever you use Codex, and get to work.
learn.chatgpt.com/docs/cloud
6
7
156
27,488
Start a task in the cloud, then follow its progress and steer Codex from your phone or another computer, even with your laptop off.
We’re also bringing the familiar desktop app experience to web and mobile.
30
26
410
112,652
You can finally close your laptop now and your agents will keep working.
Codex cloud environments are here.
Reusable environments mean less setup and faster starts, with your repo, dependencies, scripts, and settings already in place.
260
381
5,644
634,375
Ultrafast is our fastest way to build with Astra yet: in Codex, it runs up to 8x faster than Astra Standard and 4x faster than Astra Fast.
Bring your ideas to life as fast as you can type them.
84
76
1,092
143,784
On deliberately difficult factuality prompts, GPT-6.1 Sol reduces responses containing factual errors by about 32% versus GPT-6 Sol at low reasoning effort.
In our automated safety review evaluation, we observed no attempts to bypass the safety reviewer.
2
4
118
20,529
On AutomationBench, GPT-6.1 Sol scores 31.7% at medium reasoning effort, up 4.8 percentage points from GPT-6 Sol at the same setting.
On OSWorld 2.0’s offline set, it scores 71.4% versus Astra’s 73.5%, both at maximum reasoning effort, at roughly one-seventh of Astra’s cost per task.
3
6
123
14,779
On DeepSWE v1.1, GPT-6.1 Sol achieves 75.2% at high reasoning effort, surpassing GPT-6 Sol’s best score of 68.8% at maximum effort, at approximately 76% lower cost per task.
5
17
256
18,089
API pricing is $2 per million input tokens and $10 per million output tokens.
Cached input is just $0.10 per million tokens—95% less than standard input pricing and 50% less than GPT‑6 Sol’s cached input pricing.
Near-Astra performance for sustained, multi-step workloads.
12
19
280
28,354
GPT-6.1 Sol is here.
Upgraded with stronger agentic coding and computer use, near-Astra performance, and cached input at a 95% discount to standard input pricing.
GPT-6.1 Sol is built for complex refactors, deep codebase investigations, and long-running agents across apps.
270
614
8,318
483,338
dots.
An always-on agent with its own cloud computer and access to your plugins and context.
Powered by GPT-6 Astra, your dot proactively keeps your projects moving.
Here’s what developers can hand off to their dot:
– Triage recurring bug reports and feature requests across your connected apps.
– Scope failing builds and feature improvements around your priorities.
– Build and test changes with Codex, then bring back complete PRs for your review.
Open your dot’s cloud computer to inspect the work, or connect your own so it can work with your local files and code.
199
211
2,789
232,711
We saved you a seat.
See you tomorrow for the OpenAI DevDay keynote:
openai.com/live/
376
473
10,893
902,934
JupyterLite WebMCP brings an agent into your live notebook to edit cells, run code and review changes together.
Built by Allison Coleman and Juan Mendoza.
devpost.com/software/jupyter…
8
4
59
16,301
Faraday by @thegreataxios lets an agent navigate 3D scans through WebMCP while the scan stays in the browser.
Built for research and education.
devpost.com/software/faraday…
3
2
51
18,263
Bouquet Studio turns “warmer” or “less formal” into flowers you can see and rearrange together, using WebMCP.
Built by @janechao_dev and Luis Cesar Morales.
devpost.com/software/bouquet…
1
4
42
15,895
Observatory by Martin Hooijmans lets you and an agent build fantasy maps through WebMCP, with terrain, rooms and labels you can keep editing.
devpost.com/software/observa…
1
2
43
10,148
Mandate by Harzer Heribert turns your choice of CRM records, fields and a time limit into scoped WebMCP tools for an agent.
devpost.com/software/mandate…
2
1
45
11,618
Roque Nights by @sebasmediaprod helps you plan a night under the stars.
Through WebMCP, an agent can compare nights, find visible targets and propose an observing plan for you to review.
devpost.com/software/roque-n…
3
2
48
14,862
Aisle takes on the wedding seating puzzle with a WebMCP agent that respects guest relationships and pinned seats.
Built by Eri Alipaj.
devpost.com/software/aisle-a…
4
1
52
13,512
ArchMorph lets you design a home alongside an agent, then walk through it in 3D.
Built by @xmusfk, it uses WebMCP tools to edit and check the same live building model.
devpost.com/software/archmor…
2
4
105
15,003
Alza turns a floor-plan photo into an editable 2D/3D model, with a WebMCP agent that checks the geometry as you go.
Built by Elioz 404.
devpost.com/software/alza
3
3
174
20,030
MASIL uses WebMCP to help Korean elders practice calligraphy and play Janggi alongside an agent.
Built by SonSangjoon.
devpost.com/software/masil-r…
11
8
151
35,477
Meet the winners of The WebMCP Challenge.
These 10 projects show what people and agents can build together when websites expose structured tools agents can use.
🧵 See the winning projects and the builders behind them:
94
128
1,581
262,691
OpenAI DevDay roll call
Where are you joining us from, and what are you building?
930
233
6,342
437,331
We’ve fixed a bug that was degrading image understanding in GPT-6 Sol and GPT-6 Luna. You should now see better results on visual tasks in the API and Codex, including computer use.
260
306
6,062
701,708
With GPT-Live-1, Proaction is building voice agents that talk to drivers, call repair shops and help arrange vehicle maintenance, with the team stepping in when needed.
11
2
74
27,755
GPT-6 Astra helps Proaction build fleet-management agents faster, with shorter computer-use runs to get the same work done.
78
33
634
74,426
GPT-6 Astra helps @harvey turn stacks of documents into structured legal drafts, so lawyers can focus more on strategy.
72
38
614
65,667
GPT-Live-1 handles the conversation while the Raspberry Pi sends research and tool tasks to GPT-5.6 Luna via the Responses API.
The Pi’s local renderer turns scenes into 128 × 64 pixels.
Sid can keep talking while research and rendering happen in the background.
12
5
100
22,789
From figuring out the wiring to debugging “show that on the wall,” @sidrampally shares how he used Codex to turn an LED display into a voice-controlled assistant.
Powered by GPT-Live-1 and a Raspberry Pi, it shows weather, subway arrivals, and more:
56
43
691
70,281
Get lost in your side projects.
One builder at our GPT-6 hackathons brought real star maps and Astra to help you find your way home.
33
29
618
68,498
See what’s being reused and what’s preventing cache hits.
Track cache-hit rates in the new Prompt Caching Dashboard on platform.openai.com.
Use the diagnostics API to identify changes that prevented reuse and estimate how many tokens were affected.
4
4
156
24,355
With improved prompt caching in GPT-6, agents do less redundant processing behind the scenes.
More context stays reusable as reasoning effort and tool availability change, making responses faster and cheaper.
4
4
178
60,655
On AutomationBench, which measures whether AI models can complete real business workflows across apps, GPT-6 Sol (xhigh) leads Fable 5.1 (max with Opus 5 fallback) with 88% lower reported cost per task.
6
5
175
22,445
On DeepSWE v1.1, which tests coding agents on long-horizon engineering tasks, GPT-6 Sol (max) nearly matches Claude Fable 5 (xhigh) at ~80% lower cost per task.
GPT-6 Luna (max) is comparable to Fable 5 (medium) at 96% lower cost per task.
19
33
555
78,676
Improvements in caching and inference let us deliver GPT-6 Sol and GPT-6 Luna at lower cost.
We’re passing those savings on through lower API prices. Sol and Luna deliver more intelligence at half of the previous generation’s API prices, making more complex work practical to automate at scale.
13
56
783
80,026
GPT-6 Sol and Luna just landed in Astra’s orbit.
Both launch today with API prices 50% lower than GPT-5.6.
Build with Sol. Scale with Luna. To production and beyond.
283
754
9,654
980,388
GPT-6 Astra helps @cognition’s Devin back up “it works” with tests before the team ships.
63
52
817
94,727
GPT-6 Astra in Codex is helping test code end to end at @perplexity_ai.
@randomjohnnyh uses it to build test harnesses and mock third-party API responses, so he can check how the pieces work together.
144
77
1,181
115,847
In Codex, use Life Sciences plugins across genomic, protein structure, and translational research workflows, from sourcing biological evidence to generating QC reports and interactive notebooks.
12
3
95
31,738
Bring stronger biological reasoning to your research with GPT-Rosalind in the API and Codex.
Connect findings across papers and experimental results, weigh the evidence for a biological target, and work through an analysis to plan what to test next.
86
97
1,226
151,789
Habitat is OpenAI's online storage platform that powers everything from ChatGPT to Codex.
It has grown over 10x year over year. Before the Rust rewrite, its Python service handled more than 20 million requests per second at peak.
130
352
5,562
774,768
Restaurant reservations don’t always follow a script.
GPT-Live-1 listens while it speaks, so callers can interrupt, add details, or change direction mid-conversation.
Hear how @Yelp is using it to make reservation calls feel more natural:
66
45
913
104,599