Fwiw, OpenAI does have a decent active API model family of GPT-4.1 with a 1M context. But yes, the context of the GPT-5 models is terrible in comparison, and it's altogether atrocious for the GPT-5-Chat model.

The biggest issue in ChatGPT right now is a very inconsistent experience, presumably due to smaller models getting used even for paid users with complex questions.

Doesn’t it matter more what context they provide via Claude Code and Codex CLI? And arent they similar anyway there?

Because the API with maximum context is very expensive (also not rolled out to everyone)