Qatar Central Loses GPT-5-4 Mini

· AI summary
12 new1 regressions0 parked
Daily executive summary

Compared with the 2026-07-17 snapshot, the 2026-07-18 scan recorded 12 new listings, 1 regression, and 0 parked unknown transitions.

Representative changes: GPT-5 4 mini model from OpenAI (version 2026-03-17) was no longer listed in qatarcentral; model router model from OpenAI (version 2025-05-19) was newly listed in 4 regions; model router model from OpenAI (version 2025-08-07) was newly listed in 4 regions.

What changed: 1 first recorded disappearance, 12 net-new regional listings.

What this means: Review the 1 regression against existing regional targets and fallbacks first; treat the 12 new listings as options to validate. These are read-only catalog/list signals, not quota, capacity, or deployment results. Zero new delistings does not establish recovery of earlier missing listings.

7-day context (2026-07-12 to 2026-07-18): across 7 recorded scans, there were 1,787 new listings and 910 regressions. New listings led on 4 scans; regressions led on 3.

Archived commentary and representative evidence

Azure AI models in qatarcentral now show aiModels.openai.gpt-5-4-mini.2026-03-17 as unavailable after 58 available days in a 67-day history. This is a deprecation candidate rather than a confirmed retirement, but it does reduce one model/version option in the Middle East from 30/64 covered regions to 29/64.

Operationally, that means teams using Qatar Central should re-check deployment targets, fallback model/version choices, and any residency or latency assumptions tied to that region. The monitor records 13.4% unavailable time for this feature, with no prior disappearances, so this is the first observed drop rather than a recurring churn pattern.

At the same time, the model-router feature set expanded into new regions. In South America, brazilsouth is the first observed region for aiModels.openai.model-router.2025-05-19, .2025-08-07, and .2025-11-18. That broadens placement choices for routing-driven workloads where latency and data residency matter.

North America and Europe also picked up the same router versions in eastus, northcentralus, and polandcentral. The rollout lifts feature coverage from 5/64 to 9/64 regions, with same-day additions across brazilsouth, eastus, northcentralus, and polandcentral.

These router signals matter for capacity planning and model selection because they add regional options for inference routing without changing the feature note’s core use case: evaluating model capabilities, deployment options, latency, and data residency.

Engineering context

  • qatarcentral aiModels.openai.gpt-5-4-mini.2026-03-17 available → unavailable deprecation candidate
    unavailable 9/67 prior days (13.4%)coverage 29/64 monitored regions (45.3%, -1 region)coverage removed from 3.3% of prior regionsMiddle East: 1 current, 2 prior
    Still available in australiaeast, brazilsouth, canadacentral, canadaeast, centralus, eastus, and 23 more. Use this to evaluate model capabilities, regional deployment options, latency, and data residency. Azure OpenAI model availability
  • brazilsouth aiModels.openai.model-router.2025-05-19 unavailable → available net-new regional availability
    unavailable 67/67 prior days (100.0%)coverage 9/64 monitored regions (14.1%, +4 regions)South America: 1 current, 0 priorfirst observed in South America
    Also newly available in brazilsouth, eastus, northcentralus, polandcentral. Use this to evaluate model capabilities, regional deployment options, latency, and data residency. Azure OpenAI model availability
  • brazilsouth aiModels.openai.model-router.2025-08-07 unavailable → available net-new regional availability
    unavailable 67/67 prior days (100.0%)coverage 9/64 monitored regions (14.1%, +4 regions)South America: 1 current, 0 priorfirst observed in South America
    Also newly available in brazilsouth, eastus, northcentralus, polandcentral. Use this to evaluate model capabilities, regional deployment options, latency, and data residency. Azure OpenAI model availability
  • brazilsouth aiModels.openai.model-router.2025-11-18 unavailable → available net-new regional availability
    unavailable 67/67 prior days (100.0%)coverage 9/64 monitored regions (14.1%, +4 regions)South America: 1 current, 0 priorfirst observed in South America
    Also newly available in brazilsouth, eastus, northcentralus, polandcentral. Use this to evaluate model capabilities, regional deployment options, latency, and data residency. Azure OpenAI model availability
  • eastus aiModels.openai.model-router.2025-05-19 unavailable → available net-new regional availability
    unavailable 67/67 prior days (100.0%)coverage 9/64 monitored regions (14.1%, +4 regions)North America: 4 current, 2 priorregional expansion of an existing signal
    Also newly available in brazilsouth, eastus, northcentralus, polandcentral. Use this to evaluate model capabilities, regional deployment options, latency, and data residency. Azure OpenAI model availability
  • eastus aiModels.openai.model-router.2025-08-07 unavailable → available net-new regional availability
    unavailable 67/67 prior days (100.0%)coverage 9/64 monitored regions (14.1%, +4 regions)North America: 4 current, 2 priorregional expansion of an existing signal
    Also newly available in brazilsouth, eastus, northcentralus, polandcentral. Use this to evaluate model capabilities, regional deployment options, latency, and data residency. Azure OpenAI model availability
  • eastus aiModels.openai.model-router.2025-11-18 unavailable → available net-new regional availability
    unavailable 67/67 prior days (100.0%)coverage 9/64 monitored regions (14.1%, +4 regions)North America: 4 current, 2 priorregional expansion of an existing signal
    Also newly available in brazilsouth, eastus, northcentralus, polandcentral. Use this to evaluate model capabilities, regional deployment options, latency, and data residency. Azure OpenAI model availability
  • northcentralus aiModels.openai.model-router.2025-05-19 unavailable → available net-new regional availability
    unavailable 67/67 prior days (100.0%)coverage 9/64 monitored regions (14.1%, +4 regions)North America: 4 current, 2 priorregional expansion of an existing signal
    Also newly available in brazilsouth, eastus, northcentralus, polandcentral. Use this to evaluate model capabilities, regional deployment options, latency, and data residency. Azure OpenAI model availability
  • northcentralus aiModels.openai.model-router.2025-08-07 unavailable → available net-new regional availability
    unavailable 67/67 prior days (100.0%)coverage 9/64 monitored regions (14.1%, +4 regions)North America: 4 current, 2 priorregional expansion of an existing signal
    Also newly available in brazilsouth, eastus, northcentralus, polandcentral. Use this to evaluate model capabilities, regional deployment options, latency, and data residency. Azure OpenAI model availability
  • northcentralus aiModels.openai.model-router.2025-11-18 unavailable → available net-new regional availability
    unavailable 67/67 prior days (100.0%)coverage 9/64 monitored regions (14.1%, +4 regions)North America: 4 current, 2 priorregional expansion of an existing signal
    Also newly available in brazilsouth, eastus, northcentralus, polandcentral. Use this to evaluate model capabilities, regional deployment options, latency, and data residency. Azure OpenAI model availability

Generated from the monitor's structured change evidence. See the status meanings for what each signal proves, or browse all posts.

Help make this page clearer

Two short answers; GitHub will open a draft for your review. No Forms, token, or automatic submission.

This repository is public. Review the text and image for private details. Opening the draft sends text/context to GitHub in its URL. Pasting or attaching an image uploads it to GitHub immediately.

Describe the desired outcome in plain text. This becomes the issue's ### Objective. After reviewing the issue, a maintainer can add azure-backlog to queue it for a scheduled agent; the website does not add that label or start a run.

Page context included in the draft

Nothing is posted by this website. Sign in to GitHub if needed, review, attach your screenshot, and choose Submit. Closing this panel clears the local draft and screenshot.