Codex Desktop drops configured service_tier while CLI forwards it correctly, issue shows
okumurays · ghdev · 2026-10-13
A GitHub issue on openai/codex (#53649) reports that Codex Desktop (26.1007.21434) omits the servicetier parameter when using a custom provider, while Codex CLI (0.162.1) forwards it correctly with the same config.toml.
The author captured requests through a local LiteLLM proxy backed by Azure OpenAI (model gpt-6-sol, Responses API):
- curl: sends priority, HTTP 200
- Codex CLI: sends priority, HTTP 200
- Codex Desktop: parameter absent, HTTP 200
Desktop also offers no Fast mode option in its model selector, leaving no way to enable Priority Processing for this setup. The author asks that Desktop forward the explicitly configured servicetier to the Responses API.
More from coding & agent
- Mubit open-sources Banyan Sapling, a verification model with calibrated probabilities (Apache 2.0) — testingcatalog · 2026-10-24
- Hermes Watch: Open-source agent runs voice Q&A on an Amazfit smartwatch — Teknium · 2026-10-24
- Bug Hunt Bench: blind-graded leaderboard pits frontier coding models against 105 real planted bugs — PawelHuryn · 2026-10-24
- OpenAI Dots now drive on-machine sessions without spawning new Codex sessions — brandon_galang · 2026-10-24
- Dev open-sources optimAIzr after finding 56% of AI coding costs went to rereading context — stichstichstich · 2026-10-24
- AI Colab Meetup Tuesday: Agents, Memory, WebMCP on Agenda — JnBrymn · 2026-10-24