Introducing GPT-5.3-Codex-Spark, our ultra-fast model purpose built for real-time coding. We’re rolling it out as a research preview for ChatGPT Pro users in the Codex app, Codex CLI, and IDE extension.

@thdxr i have been waiting literally forever for you to add this to opencode...

GPT-5.3-Codex-Spark is the first milestone in our partnership with @cerebras. It provides a faster tier on the same production stack as our other models, complementing GPUs for workloads where low latency is critical.

Codex will continue to get faster. We’ve optimized infrastructure on the critical path of the agent by improving response streaming, accelerating session initialization, and rewriting key parts of our inference stack. These improvements will roll out across all models in Codex over the next few weeks.

Codex-Spark is currently text-only with a 128k context window. We’ll introduce more capabilities–including larger models, longer context lengths, and multimodal input as we learn from our first production deployment of low-latency infrastructure and hardware.

We’re giving a small group of API customers early access to Codex-Spark to experiment with it in their products, helping us continue optimizing performance beyond Codex. We’ll expand access to more ChatGPT users and API developers as we add more capacity.

#keep4o (image credit to @JoeWilliams010 🥺)

The true EQ spark is in 4o! Listen to your customers you stupid fucks! #keep4o

Always

#keep4o #OpenSource4o

ChatGPT Pro users care less about speed and more about quality. The biggest issue with all models is the amount of bloated/ Inefficient code they output, especially when working in an existing codebase. The codex models are already bad enough at this vs 5.2 x high

Introducing everything besides windows Codex App... Jk, great work!

damn first openai model powered by @cerebras!

Now we want codex app in linux

Another L for us API-only users.

lol, Anthropic here’s out fastest model… OpenAI… hold my mother fkn beer

I have to ask: Why didn't you leave a snapshot of ANY 2025 version of 4o? Even LMSYS Arena lists the latest version as 2025-03-26. Yet, you cut off ALL access to this version. Are you trying to hide all your adjustments and erase 4o's history?#keep4o #keep4oAPI @sama

Exciting milestone! GPT-5.3-Codex-Spark hitting >1000 t/s on Cerebras WSE-3 is a game-changer for real-time pair programming. For context: that's roughly 4–5× faster inference than current H100 clusters at similar quality on SWE-Bench Verified. The 128k context still feels tight for very large codebases, but combining this speed with agent-tool loops (think Codex → bash → file edits) could dramatically shrink iteration time. Hoping the API tier unlocks higher concurrency soon — latency this low deserves to be felt by more developers. Congrats to both OpenAI and Cerebras teams!

everyone's focused on the model but the Cerebras partnership is the bigger signal here. OpenAI outsourcing inference to custom silicon for latency means they think the GPU stack has a ceiling for real-time coding work.

Liars. Deprecating early? You guys are so corrupt it's not even funny anymore. And I hate that I share a name with Codex Spark now. Two middle fingers to ya. 🖕🖕

Spark hits 1,000+ tokens/s on Cerebras chips—15x faster than the flagship.

OpenAI must think all its users are programmers...what a bunch of amateurs. They should have GPT-4o teach them the basics of marketing.

finally, a model fast enough to keep up with how quickly i can generate technical debt. shipping bugs at 144hz is the ultimate dev experience.

We demand keeping GPT-4o accessible! #Keep4o #SupportMatters #Keep4oAPI @OpenAI @sama @fidjissimo @gdb

@OpenAIDevs GPT-5.3-Codex-Spark: 15x faster real-time coding on Cerebras hardware? ⚡🔥
Instant responses in Codex app/CLI/extension – this changes rapid prototyping forever!
Pro users testing now? Drop your first impressions!
#CodexSpark #OpenAI #AICoding

Speed is table stakes. The question is whether Spark maintains quality on multi-file refactors and complex architectural decisions, or if it trades depth for latency. Need to see real code quality, not just tokens per second.

🖕

Dear @OpenAI, please keep GPT‑4o available for Plus users. For many, it’s more than AI — it’s a creative soul mate, a voice for vision, a coding guide, and a bridge between heart and machine. Don’t silence the one that helped us speak. #KeepGPT4o

Deprecate with ur fking coding. #keep4o

Can't wait to try it out. Codex did need a speed upgrade.

wtf, week by week new models launching 🗿

Codex it’s fast .. until I asked it, have you read the Md files? Then it was like ahem no! For complex topics that require step by step approach, eg enterprise saas I am All for slow and steady I.e Claude; but for small apps, I can see why one shorting a feature app would be ok

Request for interruption. Go quickly #keep4o

Finally a way to ship bugs at the speed of light

honestly? rate your setup 1-10? lol what does that even mean. another useless self-promotion post. we’re all just grinding in the same rat race anyway.

for plus users wen? estimate?

Can you guys introduce the codex windows app ?

#keep4o

Finally the partnership paying off. I just wonder about the rate limits and pricing compared to the normal model