AI Agent StoreCloudflare · Preview API verified
Clairic · Cloudflare
Turn an invoice or screenshot into useful fields, such as an amount, due date or estimated payment time. Missing values and uncertain predictions need different handling.
First reviewed 2026-10-20 · Checked 2026-11-03. The launch date has not been confirmed.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on records with known answers, including cases that should go to a person.
What you can use today
Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.
Exact provider API ID: @cf/cloudflare/clairic. Returns text spans, numbers, dates, lists, estimates and forecasts with uncertainty information. A valid format or high confidence does not guarantee a correct value. Estimates can still be returned when evidence is sparse; check important results before acting.
Available as a Workers AI preview. It extracts or predicts values, which makes it different from a model that only chooses among your predefined answers.
The model page advertises 65,536 context tokens, while its schema splits fields across 8,192-token processing passes. Check whether the response reports truncated input, and use its usage totals for billing. Up to four embedded PNG/JPEG/WebP images: 4 MiB each, 8 MiB total decoded and a 16 MiB request body; no remote image URLs.
Cloudflare lists $0.10 per million input tokens. A separate output rate and cached-input policy are not verified. Several processing passes can be needed; use reported input_tokens rather than the original text length. Include retries when comparing the total cost.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.
Compare caching and long-context costs ↗