Introducing Clairic, a new System One class of extraction models

Summary

Cloudflare announces Clairic, a preview extraction model hosted on Workers AI, designed as a System One model for fast, one-pass value extraction from unstructured inputs. Unlike decision models such as Jev or Clef that output probabilities, Clairic returns extracted, computed, estimated, or forecasted typed values like numbers, dates, durations, and spans with character offsets and confidence scores. It processes only input tokens in a single forward pass, resulting in under-one-second responses and no output token charges, ensuring every answer is a valid typed value or null. The model handles extraction tasks like invoice numbers, estimation with distributions providing a median and 80% interval, and forecasting per future step with intervals, all without token generation. Cloudflare plans to release Clairic as open-weights soon and offers it via Workers AI with a typed field request structure accessible through env.AI.run() or the REST API.

Takeaways

1. 1

   Clairic extracts, computes, estimates, and forecasts typed values (numbers, dates, durations, spans) from unstructured inputs in a single forward pass, returning confidence scores and character offsets for each result.

2. 2

   Unlike LLMs that charge for output tokens and may produce invalid responses, Clairic generates no output tokens, ensuring every answer is a valid typed value or null, with responses typically under one second.

3. 3

   Clairic is designed for extraction tasks where LLMs are inefficient, such as invoice data extraction, delivery date estimation, and traffic forecasting, and is available as a preview on Workers AI with plans for open-weight release.

FAQ