WHAT NEW IN X11.02 MON

AI collections from X · 22 collections · 65,263 posts

gpt-6IMAGE

GPT-6.1 Sol: Codex vs API speed and usage tested

A hands-on test finds 6.1 Sol in Codex runs at half the API's speed in regular mode, and Ultrafast consumes three times the usage OpenAI claimed.

Youssof Al Toukhi
@Youssofal_Archived 23 days agoOriginally posted 2026.10.09
GPT-6.1 Sol: Codex vs API speed and usage tested
Youssof Al Toukhi @Youssofal_Originally posted 2026.10.09
Open original on X

I tested GPT 6.1 Sol in Codex vs API with Ultrafast. Ultrafast is actually marginally faster in Codex vs the API. Within variance. However, on regular fast mode 6.1 Sol is half as fast in codex vs API (42 vs 88 TPS) The BIGGEST problem is the usage. OpenAI claimed 20% higher usage than regular Astra. In truth it is 60%. In Codex, ultrafast uses limits 8x faster rather than the 6x API cost. This means 6.1 Sol ultrafast = 1.6x usage of Astra regular.

x.com/youssofal_/status/2108542066150047807Archived 2026.10.10 10:02