OpenAI Platform & APIs$ explicitmediumCluster of 2 signals
Card #2113 · OpenAI Platform & APIs

Forced migration to expensive Codex models with degraded performance

Users are frustrated by the removal of older, more efficient Codex models, forcing them onto more expensive versions like GPT-5.4 and 5.5. These newer models are perceived as harder to control, requiring different prompting styles to achieve similar results, and consuming tokens much faster.

OpenAI Platform & APIsUpdated Jun 6, 20260.18
Pain score
0.18/ 1.00 · weighted product of four components
Reach0.32
distinct authors (log-normalized)
Recency1.00
freshness decay, half-life months
Engagement1.00
upvotes + comments, normalized
Monetization1.00
willingness-to-pay cues in evidence
§ Evidence — 3 verified quotes
They have unceremoniously just rug-pulled the only good model off the extension. Not only that, but now we are forced to use 5.4 or 5.5 models and they are VASTLY more expensive.
Forum·@GlassAcres··source ↗
GPT-5.4 suddenly became much harder to control, while GPT-5.5 works properly again. This inevitably creates the impression that users are being pushed, indirectly, toward the newer and more expensive model.
Forum·@LEFTERIS1··source ↗
having to completely change language and style to get similar results with no other option is incredibly frustrating.
Forum·@GlassAcres··source ↗

Comments are a Pro feature — join the conversation, share what you've shipped, hear what others are building.

Upgrade to Pro