Cloudflare launches Clairic, a new extraction model class claiming higher accuracy and lower cost than LLMs
ritakozlov · x · 2026-10-20
Cloudflare announced Clairic, the first of a new "System One"-style class of extraction models, now in preview on Workers AI as @cf/cloudflare/clairic, with open weights coming soon.
- Inspired by TypeSafe's System One model concept (from Kahneman's Thinking, Fast and Slow): fast, precise, purpose-fit models vs. deliberate LLM reasoning
- Clairic extracts, computes, estimates and forecasts values from unstructured inputs — invoice totals, delivery delays, repair cost estimates, traffic forecasts
- Targets the flood of repetitive structured-output calls to frontier LLMs, promising higher accuracy, lower latency and cheaper cost
More from Infra
- Celesto launches cloud computers for agents, claims 96% cheaper CI than GitHub runners — aniketmaurya · 2026-10-20
- NVIDIA's first GB300 FP4 counter-submission still 1.64x worse perf per dollar than TPUv7 — xennygrimmato_ · 2026-10-20
- Long queues at RTX Spark SF launch for local Qwen demos built with ODS software — TheZachMueller · 2026-10-20
- Dream-1 Beta runs robot tasks at $1.72 per success, up to 41x cheaper than LLM agents — gharik · 2026-10-20
- Arm AGI CPU posts 2x end-to-end agentic workflow performance vs leading x86 in Signal65 tests — ryanshrout · 2026-10-20
- Loop engineering is a teeter-totter: you never have enough CPU cores and inference at once — kieranklaassen · 2026-10-20