OpenAI API — January, 2026

January 1, 2026

This release introduces the gpt-5.2-codex model, optimized for agentic coding tasks, and the Open Responses specification, promoting interoperable LLM interfaces across providers. Dedicated SIP IP ranges have been added for the Realtime API, enhancing GeoIP routing. Several model slugs, including gpt-realtime-mini, sora-2, and gpt-4o-mini-tts, have been updated to their latest snapshots, improving performance and accuracy. A fix addresses an issue where image edits through /v1/images/edits incorrectly used high fidelity.

Added

Released gpt-5.2-codex to the Responses API. GPT-5.2-Codex is a version of GPT-5.2 optimized for agentic coding tasks in Codex or similar environments. Read more here.
Added dedicated SIP IP ranges for Realtime API. sip.api.openai.com does GeoIP routing, and will direct SIP traffic to the closest region. Learn more.

Changed

Announced Open Responses: an open-source spec for building multi-provider, interoperable LLM interfaces built on top of the original OpenAI Responses API.
Updated the gpt-realtime-mini and gpt-audio-mini slugs to point to the 2025-12-15 snapshots. If you need the previous model snapshots, use gpt-realtime-mini-2025-10-06 and gpt-audio-mini-2025-10-06.
Updated the sora-2 slug to point to sora-2-2025-12-08. If you need the previous model snapshot, use sora-2-2025-10-06.
Updated the gpt-4o-mini-tts and gpt-4o-mini-transcribe slugs to point to the 2025-12-15 snapshots. If you need the previous model snapshots, use gpt-4o-mini-tts-2025-03-20 and gpt-4o-mini-transcribe-2025-03-20. We currently recomend using gpt-4o-mini-transcribe over gpt-4o-transcribe for the best results.

Fixed

Fixed an issue where gpt-image-1.5 and chatgpt-image-latest were incorrectly using high fidelity for image edits through /v1/images/edits, even when fidelity was explicitly set to low (the default).