{"slug": "deepseek-deepseek-v4-flash-open-inference-fp8-b3it-change-tv-0-52", "title": "deepseek/deepseek-v4-flash @ open-inference/fp8: B3IT change (TV 0.52)", "summary": "Monitoring of the deepseek/deepseek-v4-flash endpoint on open-inference/fp8 was retired with no border inputs found since 2026-09-24, and its logprob tracking stalled after recent queries failed, according to the tracking dashboard. The endpoint's B3IT detector recorded a total-variation level shift of 0.52, while cumulative OpenRouter tracking spend reached $0.23 across 58,205 queries, $0.21 of it in the last 30 days.", "body_md": "## Tracking status\n\nLT\n\n**stalled**— We tracked this endpoint's logprobs, but its recent queries all failed, so tracking stopped.\nB3IT\n\n**retired · no bis**— Monitoring was retired: we could not find enough border inputs for this endpoint. (since 2026-09-24)\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 2026-08-01\nTotal to date\n\n$0.23\n\nLast 30 days\n\n$0.21\n\nQueries\n\n58,205\n\n- B3IT (onboarding)$0.2195%\n- B3IT (monitoring)$0.0115%\n- LT$0.00020<1%\n- Vetting$0.000030<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/deepseek-deepseek-v4-flash-open-inference-fp8-b3it-change-tv-0-52", "canonical_source": "https://www.trackllm.net/endpoints/deepseek2fdeepseek-v4-flash23open-inference2ffp8.html", "published_at": "2026-09-22 23:22:48+00:00", "updated_at": "2026-09-25 02:01:34.614377+00:00", "lang": "en", "topics": ["ai-infrastructure", "large-language-models"], "entities": ["DeepSeek", "deepseek-v4-flash", "open-inference", "OpenRouter"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/deepseek-deepseek-v4-flash-open-inference-fp8-b3it-change-tv-0-52", "markdown": "https://wpnews.pro/news/deepseek-deepseek-v4-flash-open-inference-fp8-b3it-change-tv-0-52.md", "text": "https://wpnews.pro/news/deepseek-deepseek-v4-flash-open-inference-fp8-b3it-change-tv-0-52.txt", "jsonld": "https://wpnews.pro/news/deepseek-deepseek-v4-flash-open-inference-fp8-b3it-change-tv-0-52.jsonld"}}