Model Census pings every hosted LLM daily to see which providers still serve it
Lari_island · x · 2026-10-09
Model Census is a monitoring site that daily scrapes OpenRouter, Vercel AI Gateway, Amazon Bedrock (multiple regions), the Anthropic API, and Anthropic/OpenAI deprecation pages, then makes a real test call to every listed text model — verifying which providers still actually serve each model, stated end dates, and what changed. For open-weight models it also checks whether Hugging Face weights remain public.
Not yet covered: Vertex, Azure, and smaller providers. It emerged from a question about which channels still serve the retired Claude 3.6.
More from Models
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23
- Marker's lite mode scores 75.1 vs 42.3 for Azure Read on OmniParseBench — VikParuchuri · 2026-10-23
- Datalab launches lite OCR at $0.50 per 1,000 pages, 20-30x cheaper than Azure, Google and AWS layout APIs — VikParuchuri · 2026-10-23
- LiveNerf's 29-day data finds no nerfing of Claude Opus 5.5 — TheOnlyVibemaster · 2026-10-23
- PHP Foundation reveals Anthropic's Claude cyber model scanned PHP, validated with OpenAI's Daybreak Red — saibharadwaj · 2026-10-23