ModelClock
Capability change
Capability change announced Feb 3, 2026
OpenAI documents a capability change: “Feb 3 Update · Model: gpt-5.2 · Model: gpt-5.2-codex We have optimized our inference stack for API customers and GPT-5.2 and GPT-5.2-Codex now run ~40% faster.”
- Hosting route
- First-party API
- Affected scope
- Not stated in the notice
- Announced
- Feb 3, 2026
- First seen by ModelClock
- Oct 5, 2026
What the provider published
developers.openai.com ↗Feb 3
Update · Model: gpt-5.2 · Model: gpt-5.2-codex
We have optimized our inference stack for API customers and GPT-5.2 and GPT-5.2-Codex now run ~40% faster. Model and model weights are unchanged.
Read from the provider's text; the quote is the provider's exact lines.
