Codex CLI bug exposes inconsistent gpt-6.1-sol Ultrafast tier filtering by originator header
yamashirotakashi · ghdev · 2026-10-10
A developer filed an issue showing that with ChatGPT auth on the official Codex CLI 0.162.1, the gpt-6.1-sol model catalog only advertises the priority tier, so a requested ultrafast tier silently resolves to default.
A controlled test kept the account, auth, URL, and headers constant and varied only the originator header against chatgpt.com/backend-api/codex/models: responses differed in Sol's speed/service tiers (e.g. fast/priority) across clients, all HTTP 200. Local telemetry confirmed servicetier stayed at default.
The author asks OpenAI to investigate whether first-party catalog filtering matches the intended Sol Ultrafast rollout and account eligibility — implicitly hinting the ultrafast tier is being gated or partially rolled out.
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23