GPT-5.3-codex-spark is being retired. The statement "Time to make room for the future" sounds to me like a successor is in the works.
I would really like a GPT-6-Spark. 5.3-codex-spark was an incredibly fast model, up to 1000 tokens/second. Therefore, I would be very happy with a successor that also offers extra rates when the plan is exhausted.
Next week we’ll be retiring GPT-5.3-Codex-Spark. Can you believe we shipped a model named as such!! It's had a good run and was a lot of fun, but usage has been...