Cloudflare Launches Clairic, a System One-Style Extraction Model Faster and Cheaper Than LLMs
michellechen · x · 2026-11-04
Cloudflare announced a preview of a new class of System One-style models: extraction models. The first, Clairic, is hosted on Workers AI as @cf/cloudflare/clairic, with open weights planned soon. It extracts, computes, estimates and forecasts values from unstructured inputs at higher accuracy, lower latency and lower cost than traditional LLMs.
- Context: TypeSafe introduced System One models a month ago, inspired by Kahneman's Thinking, Fast and Slow; its Jev model targets a specific use case with probabilistic, well-typed outputs.
- Motivation: many structured-output calls to frontier LLMs repeat the same shapes (invoice total, delivery date, days late, repair cost, next-24h traffic), answers that cannot be enumerated in advance and suit a decision model.
More from Models
- Overthinking Bench: Claude burns 1,069 thinking tokens on 'is the globe round?' — intellectronica · 2026-11-04
- Andrew Ng: asking if LLMs beat specialists at their own game is now meaningless — andrewgwils · 2026-11-04
- Model Vendors Post-Train for Tool Search, Squeezing Out MCP-Layer Workarounds — pvncher · 2026-11-04
- Claude Opus 5.5 blocks viewing Qwen's reasoning, safeguard error says sorry not allowed — andpoul · 2026-11-04
- Gemini API deprecations: 2.5 Pro auto-redirects to 3.8 Flash on Dec 1 — patloeber · 2026-11-04
- Tencent's Hy4 coming to LMArena after preview hit #2 among open models in Agent Arena — arena · 2026-11-04