{"slug": "z-ai-glm-5-2-alibaba-fast-lt-change-shift-3-50", "title": "z-ai/glm-5.2 @ alibaba/fast: LT change (shift 3.50)", "summary": "A tracking dashboard recorded a log-probability level shift of 3.50 for the endpoint z-ai/glm-5.2 @ alibaba/fast, which is marked as actively tracked while the B3IT border-input signal was vetted but not selected because the selection budget went to more popular models. Tracking spend on the endpoint since 2026-09-02 totaled $0.020 across 836 queries, with $0.0063 in the last 30 days, of which LT accounted for $0.01891% and vetting $0.00189%. The page lists no dated entries in its detected-changes table.", "body_md": "## Tracking status\n\nLT\n\n**tracked**— This endpoint is actively tracked.\nB3IT\n\n**not selected**— This endpoint vetted fine, but the selection budget went to more popular models.\n## Drift from baseline\n\nBoth signals measure how far this endpoint's behavior has moved from its **reference period**. LT tracks the average change in the returned tokens' log-probabilities (nats); B3IT tracks the total-variation distance of the border-input votes (0–1). Both should ideally be as close to 0 as possible. Dashed lines mark published changes, labeled with the **level shift** across them: for LT the mean drift over the 7 days after minus the 7 days before; for B3IT the total-variation shift its detector measured.\n\nHover a day on either lane, a change mark or an epoch line to read the data behind it.\n\n## Detected changes\n\n| Date | Method | Level shift | \n|---|---|---|\n\n## Spend\n\nwhat OpenRouter billed for tracking this endpoint. Spend recorded since 2026-09-02\nTotal to date\n\n$0.020\n\nLast 30 days\n\n$0.0063\n\nQueries\n\n836\n\n- LT$0.01891%\n- Vetting$0.00189%\n\n**Vetting** is the one-off probe that checks the endpoint's billed cost against its advertised price.\n\n**B3IT (onboarding)** is the initial border-input search;\n\n**B3IT (monitoring)** and\n\n**LT** are the recurring daily checks.", "url": "https://wpnews.pro/news/z-ai-glm-5-2-alibaba-fast-lt-change-shift-3-50", "canonical_source": "https://www.trackllm.net/endpoints/z-ai2fglm-5.223alibaba2ffast.html", "published_at": "2026-11-12 11:09:15+00:00", "updated_at": "2026-11-19 22:13:21.147864+00:00", "lang": "en", "topics": ["large-language-models", "mlops"], "entities": ["z-ai/glm-5.2", "alibaba/fast", "OpenRouter", "B3IT", "LT"], "also_reported_by": [], "takeaway": "The z-ai/glm-5.2 @ alibaba/fast endpoint showed a 3.50-nat mean log-probability level shift over the 7 days after a change versus the 7 before, while its B3IT border-input signal was vetted but not selected for monitoring.", "recommendation": {"advice": "Track log-probability drift and border-input distance daily against a reference period so provider-side model changes surface as measurable level shifts rather than silent behavior changes.", "playbook": "production-ops", "playbook_url": "https://wpnews.pro/playbooks/production-ops"}, "alternates": {"html": "https://wpnews.pro/news/z-ai-glm-5-2-alibaba-fast-lt-change-shift-3-50", "markdown": "https://wpnews.pro/news/z-ai-glm-5-2-alibaba-fast-lt-change-shift-3-50.md", "text": "https://wpnews.pro/news/z-ai-glm-5-2-alibaba-fast-lt-change-shift-3-50.txt", "jsonld": "https://wpnews.pro/news/z-ai-glm-5-2-alibaba-fast-lt-change-shift-3-50.jsonld"}}