Clairic

What Clairic is

Clairic is Cloudflare’s first extraction model. Cloudflare announced it on 19 October 2026 as a preview on Workers AI, and calls it “a new class of System One-style models”. Cloudflare’s post credits TypeSafe AI with the System One idea. TypeSafe coined the term and had not commented on the new class as of 19 October 2026.

Until now every System One model on this site has been a decision model: it picks from options you list. Clairic returns values instead, read from the input, computed from it, or predicted beyond it: an invoice total, a delivery date, the days a parcel is late, a repair cost. Like Clef, it answers in one parallel pass and generates no tokens. The extraction model guide covers the class.

What it returns

You send a state (text, plus up to four images) and fields, a map of named fields. Each field has a type and optional plain-language instructions.

Every scalar answer carries value, p_null (the probability the value is not in the input), confidence and guess. When the value is missing, value is null and guess shows what the model would otherwise have picked. Estimates add a median, an 80% interval from p10 to p90, and p_below and p_above; all 99 percentiles are available on request. Forecasts return the same numbers as arrays, one per step.

The API is not Jev-compatible. It takes fields, not questions, and answers under answers.

Calling it

The invoice example from the Workers AI model page, cut to four of its six fields, called from a Worker:

const response = await env.AI.run("@cf/cloudflare/clairic", {
  model: "clairic",
  state: "Invoice INV-2291 from Northwind Supply, issued 2026-09-02, net 30. 4 pallets at $250.00 each, shipping $80.00. Contact: Dana Ruiz, Priya Shah.",
  fields: {
    invoice_number: { type: "text" },
    due_date: { type: "date", instructions: "Issue date plus the net payment days" },
    total: { type: "number", decimals: 2, unit: "USD", instructions: "Amount due including shipping" },
    po_number: { type: "text", instructions: "Purchase order number" },
  },
});

The answers block of the page’s response, for those four fields:

{
  "invoice_number": {"type": "text", "p_null": 3.8e-10, "span": [8, 16], "guess": "INV-2291", "confidence": 1, "value": "INV-2291"},
  "due_date": {"type": "date", "p_null": 1.9e-08, "guess": "2026-10-02", "confidence": 0.9999, "value": "2026-10-02"},
  "total": {"type": "number", "p_null": 2.3e-08, "guess": 1080, "confidence": 0.9999, "value": 1080},
  "po_number": {"type": "text", "p_null": 1, "span": [8, 16], "guess": "INV-2291", "confidence": 0.9995, "value": null}
}

The due date and the total appear nowhere in the text. Clairic computed both. The invoice has no PO number, so po_number comes back null with a p_null of 1.

Each field can also set a null_threshold, the p_null above which its value comes back null (0.5 by default). Number fields take 0 to 6 decimals, and a forecast takes a horizon of 1 to 64 steps. Two request options, include_quantiles and return_state_text, add the 99 percentiles to estimates and return the text that spans index into.

What Cloudflare reports

Every figure here is vendor-run. No independent board has measured Clairic as of 19 October 2026.

On 21 next-day forecasts of US airport checkpoint counts, the mean error was 3.3%, and 17 of the 21 actual counts fell inside the 80% interval. In a claims pipeline, Clairic then Clef then GLM-5.3 took 19.3 s end to end, against 61.7 s with GLM-5.3 at every step. The extract step took 0.46 s against 16.1 s. Cost per million claims was $6,032 against $11,740. The blog’s table calls that about 3.2x faster and 49% cheaper. Co-author Michelle Chen’s X thread says Cloudflare’s live demo shows the cascade 3.5x faster and 77% cheaper. The two sets of figures disagree. The demo runs live and lets you pick the LLM and its reasoning level, so its figures depend on that setup. Neither set is independent. Cloudflare says both pipelines got the facts and the decision right in every run, and Clairic’s repair estimate was the same each time.

What it’s good at

Clairic suits structured-output calls that repeat the same shape: totals, dates and durations from emails, invoices and receipt photos, including values one or two steps of arithmetic away. Cloudflare says thirty fields cost about the same as three. It also fits in front of a decision model: Clairic extracts the values, then Clef decides. Clef vs Clairic and Jev vs Clairic cover when to use which and how to chain them.

What it’s not for

Cloudflare lists the preview’s limits itself. Longer chains of dependent steps and totals across many table rows are not reliable, so “have Clairic predict the value and let code do the math.” Estimates need evidence in the input. “Calibration is measured, not guaranteed,” and intervals can run narrow on unfamiliar data. Cloudflare calls forecasting “basic” and says “the architecture makes every answer well formed, not necessarily correct.” It writes no prose and does not pick from options.

Access today

Clairic is in preview on Workers AI as @cf/cloudflare/clairic, at $0.10 per million input tokens with no output charge. Cloudflare’s terms for the model say it “may cease providing it”. Cloudflare says open weights are coming soon. Michelle Chen’s thread says the team wants to make “a few tweaks” first. Neither has given a date or licence as of 19 October 2026.

Specifications

Versions

• @cf/cloudflare/clairic, 19 Oct 2026, The preview, which Cloudflare calls an early checkpoint. Cloudflare says it intends to release the weights openly soon; co-author Michelle Chen says that comes after "a few tweaks". No date or licence published as of 19 October 2026.

Use cases

What people use Clairic for, one page per pattern.

Examples built with Clairic

The most-starred and most-viewed entries in the directory. All Clairic examples.

Introducing Clairic, a new System One class of extraction models

Cloudflare's launch post for Clairic, a preview extraction model on Workers AI that returns typed values such as spans, numbers, dates, estimates and forecasts with probabilities. It sets out extraction as a second System One class beside decision models and gives Cloudflare's own forecast and claims-pipeline results.

Cloudflare122k viewsOpenIntroducing Clairic, a new System One class of extraction models on blog.cloudflare.com

Article

Cascade vs. one LLM: Clairic, Clef and an LLM on Workers AI

Cloudflare's live demo, linked from the Clairic launch post, that sets a cascade of Clairic, Clef and an LLM on Workers AI against a single LLM. Co-author Michelle Chen's X thread says it shows the cascade 3.5x faster and 77% cheaper; the blog's own table gives about 3.2x and 49%. The demo lets you pick the LLM and its reasoning level. All figures are vendor-run.

CloudflareOpenCascade vs. one LLM: Clairic, Clef and an LLM on Workers AI on clairic-pipeline-demo.workers-ai-mle.workers.dev

Project

Benchmarks

Published scores, each linked to its source. A row marked vendor-run was measured by the vendor itself, so read it as one side's result.

• Claims pipeline (Cloudflare), End-to-end latency: Clairic, then Clef, then GLM-5.3 for the reply, against 61.7 s with GLM-5.3 at every step: about 3.2x faster in the blog's table. Co-author Michelle Chen's X thread says the live demo shows the cascade 3.5x faster. The demo runs live and lets you pick the LLM and its reasoning level, so its figures depend on that setup.
• Claims pipeline (Cloudflare), Extract step latency: Against 16.1 s for GLM-5.3 doing the same step.
• Claims pipeline (Cloudflare), Cost per million claims: Against $11,740 with GLM-5.3 at every step, 49% less in the blog's table. Michelle Chen's X thread says the live demo shows the cascade 77% cheaper. The demo runs live and lets you pick the LLM and its reasoning level, so its figures depend on that setup.
• TSA checkpoint forecast (Cloudflare), Mean error: Next-day forecasts of US airport checkpoint counts, 21 days in a row, from Cloudflare's launch post.
• TSA checkpoint forecast (Cloudflare), Days inside the 80% interval: Three of the four misses fell on the Columbus Day weekend.

Comparisons

Head-to-head pages that put Clairic against other models. Extraction models are listed apart from the decision-model tables, in their own section of the models page.

Guides