Model comparison
Clairic vs Clef
Provider-published facts for Clairic and Clef, side by side: price, limits, inputs, access and data policy. No mystery scores and no invented benchmark rankings.
Model comparison
Provider-published facts for Clairic and Clef, side by side: price, limits, inputs, access and data policy. No mystery scores and no invented benchmark rankings.
Quick take
Cloudflare's preview extraction model that turns emails, receipts and other unstructured text and images into typed values that software can use directly.
Clairic is a preview, and Cloudflare calls the current endpoint an early checkpoint. Each text field runs in its own pass and the input is billed again for every pass, so count fields when estimating cost. Long text is truncated to fit, and open weights are announced but not yet released.
Cloudflare's larger decision model for classifying information and choosing an action without generating a chat response.
This is not a chatbot and does not explain its decisions in prose. Test probability thresholds on your own examples. Hosted requests can truncate long state, and self-hosted limits depend on configuration.
Compare the published facts
Values use each provider's own published units and limits. A blank means the provider did not publish a directly comparable value in the sources reviewed.
| AI decision models | Clairic | Clef |
|---|---|---|
| Input priceCurrent provider price for the text or structured state submitted to the model, including whether decision outputs are billed. | $0.10 / 1M input tokens; output free | $0.24 / 1M input tokens |
| Input capacityMaximum documented state and question capacity for one request. | 65,536 tokens of text plus up to four images; no field limit | 65,536 tokens; up to 64 questions per request |
| Decision typesThe bounded question forms the model can answer, such as choices, scores, or probabilities. | Extraction fields: text spans, numbers, dates, times, durations, lists, estimates and forecasts | Choice, Score, and Noul probability questions |
| Output contractHow the response is constrained for direct use by application code. | One typed value per named field, or null | Typed JSON decisions defined before inference |
| UncertaintyWhether the endpoint exposes probabilities, confidence, or another calibrated signal. | Null probability and confidence per answer; 80% intervals for estimates and forecasts | Probability distributions; Choice and Score also include confidence |
| Where to use itCurrent API, SDK, playground, and access-stage information. | Workers AI binding and REST API; preview | Workers AI API and self-hosted weights |
How to choose
Start with the job you need to complete, then validate cost, access, and policy details on your exact provider route.
Cloudflare does not use Workers AI customer content to train AI models, and standard requests are not retained after the response, with limited exceptions. Features that store content follow their own terms.
Cloudflare says Workers AI customer content is not used for training or service improvement without explicit consent. Connected storage services can retain content. Self-hosted deployments follow your own storage and access controls.
Provider and API links
Frequently asked questions
Clairic: Cloudflare's preview extraction model that turns emails, receipts and other unstructured text and images into typed values that software can use directly. Clef: Cloudflare's larger decision model for classifying information and choosing an action without generating a chat response.
Best fit for Clairic: Pulling fields from emails and receipts. Best fit for Clef: Support ticket classification and routing. Test both with your own data and provider route before committing.
From each provider's own documentation, pricing and policy pages for the AI decision models category. Cody does not add its own benchmark scores or name a universal winner.