gpt-6IMAGE
GPT-6 Astra reasoning budget gap between API and Codex surfaces
The post says GPT-6 Astra gets a reasoning budget of about 832 via the API but only 128 in Codex, raising suspicion that ChatGPT runs a weakened version.
Salio
@Mr_SalioArchived 2026.09.30Originally posted 2026.09.29
Salio @Mr_SalioOriginally posted 2026.09.29
🚨 ChatGPT might be running nerfed versions of OpenAI’s own models GPT-6 Astra gets ~832 reasoning “juice” via API vs just 128 through Codex. Same model Completely different reasoning budget So API users are getting the real monster while ChatGPT users get the constrained version 💀
x.com/mr_salio/status/2104851291834908941Archived 2026.09.30 10:19