ModelClock
Capability change
Capability change announced Sep 21, 2026
Tempr Gateway documents a capability change: “OpenAI's pro and codex models — OpenAI serves models such as gpt-5-pro, o3-pro and gpt-5.3-codex only on its Responses API, so they used to fail on…”
- Hosting route
- Tempr Gateway platform
- Affected scope
- Not stated in the notice
- Announced
- Sep 21, 2026
- First seen by ModelClock
- Oct 7, 2026
What the provider published
temprhq.io ↗
- OpenAI's pro and codex models — OpenAI serves models such as
gpt-5-pro,o3-proandgpt-5.3-codexonly on its Responses API, so they used to fail on/v1/chat/completionsand/v1/messages. Tempr now bridges those calls to the Responses API and back, streaming included.
Read from the provider's text; the quote is the provider's exact lines.
