{"slug": "z-ai-glm-5-3-flash-coreweave-nvfp4-b3it-change-tv-0-30", "title": "z-ai/glm-5.3-flash @ coreweave/nvfp4: B3IT change (TV 0.30)", "summary": "OpenRouter's tracking page for the z-ai/glm-5.3-flash endpoint hosted on coreweave/nvfp4 reports a B3IT change with a total-variation distance of 0.30, while the endpoint's logprob probe failed with an HTTP 400 error because Dynamo's SGLang backend does not currently support logprobs >= 1 due to O(N) per-position detokenization. OpenRouter has billed $0.16 to date for tracking the endpoint since 2026-09-17, including $0.11 in the last 30 days across 70,354 queries, with B3IT onboarding at $0.149 and B3IT monitoring at $0.016. The page lists no detected changes in its changes table and shows the endpoint under active monitoring through its border inputs.", "body_md": "## Tracking status\n\nLT\n\n**probe failed**— This endpoint claims logprob support, but our probe could not obtain usable logprobs. (HTTP 400: ValueError: Dynamo's SGLang backend does not currently support logprobs >= 1 due to an O(N) per-position detokenization…)\nB3IT\n\n**monitoring**— This endpoint is actively monitored through its border inputs.\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 2026-09-17\nTotal to date\n\n$0.16\n\nLast 30 days\n\n$0.11\n\nQueries\n\n70,354\n\n- B3IT (onboarding)$0.1490%\n- B3IT (monitoring)$0.01610%\n- Vetting$0.000076<1%\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-5-3-flash-coreweave-nvfp4-b3it-change-tv-0-30", "canonical_source": "https://www.trackllm.net/endpoints/z-ai2fglm-5.3-flash23coreweave2fnvfp4.html", "published_at": "2026-10-13 02:19:04+00:00", "updated_at": "2026-10-22 02:10:28.310296+00:00", "lang": "en", "topics": ["large-language-models", "ai-infrastructure", "ai-tools"], "entities": ["OpenRouter", "z-ai", "glm-5.3-flash", "CoreWeave", "Dynamo", "SGLang"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/z-ai-glm-5-3-flash-coreweave-nvfp4-b3it-change-tv-0-30", "markdown": "https://wpnews.pro/news/z-ai-glm-5-3-flash-coreweave-nvfp4-b3it-change-tv-0-30.md", "text": "https://wpnews.pro/news/z-ai-glm-5-3-flash-coreweave-nvfp4-b3it-change-tv-0-30.txt", "jsonld": "https://wpnews.pro/news/z-ai-glm-5-3-flash-coreweave-nvfp4-b3it-change-tv-0-30.jsonld"}}