I keep getting “Selected model is at capacity. Please try a different model.” whenever I try to use the 5.3 Codex Spark model, I wonder what is going on!
This is extremely frustrating to see this every time I’m in the middle of an important task. Even after being a Pro member I’m seeing such issues. It’s definitely not the tier issue but the OpenAI’s.
The other thread claim to have it resolved on 18th July but, man, this keeps popping up.
Hi everyone, thanks for flagging this.
Since this was reported, GPT-5.3-Codex-Spark retired on September 14 and is no longer available in the desktop app, Codex CLI, or IDE extension. Please select a currently available model from the model guide. If your saved configuration still selects Spark, update that selection too.
If you’re seeing the same capacity message with a current model, could you share the model name, whether you’re using the desktop app, CLI, or IDE extension, and whether another model works?
~ Ziad