Cloudflare introduces Clairic, a System One model for extracting and estimating values
Original titleIntroducing Clairic, a new System One class of extraction models
Cloudflare has released a preview of Clairic, a System One extraction model hosted on Workers AI as @cf/cloudflare/clairic.
It extracts, computes, estimates, and forecasts typed values from unstructured input in a single pass, with confidence scores and 80% intervals, and no output tokens.
In the post's email-claim pipeline, Clairic and Clef ran in 19.3 seconds against 61.7 seconds for an all-LLM version, at 49% lower cost per million claims. Cloudflare says the model will be released with open weights soon.
The post separates extraction, decision, and generation steps in one pipeline, with latency and cost figures showing how the split changes the workflow.
Source: Cloudflare Blog · AI · blog.cloudflare.comPublished · added here