// AI Platform Drift
Cloudflare Workers AI adds Clairic extraction model at $0.10/M input tokens
Cloudflare developer changelog · published 2026-10-19 18:45 UTC
WHAT CHANGEDCloudflare released @cf/cloudflare/clairic on Workers AI as a preview on 2026-10-19. Clairic is an extraction model that returns typed values (text, number, date, time, duration, list, estimate, forecast) instead of generating text tokens. It processes input in one pass and guarantees valid values for requested types or null. Pricing is $0.10 per million input tokens with no output token charge because it generates no tokens. The model handles structured extraction tasks like invoice parsing, date arithmetic, and forecasting, with documented limitations in multi-step arithmetic, long-range forecasts, and calibration on unfamiliar data.
WHY IT MATTERSThis introduces a new model category for deterministic structured data extraction where you need typed values rather than text generation. The single-pass architecture and type guarantees eliminate the token-generation overhead and validation logic required when using text-completion models for extraction tasks. The preview status means arithmetic beyond one or two steps, long-range forecasts, and calibration on unfamiliar data are not yet reliable, so production use requires validation workflows using the returned confidence scores and p_null probabilities.
WHAT TO DOIf you currently use text-completion models for structured extraction (parsing invoices, forms, or documents into typed fields), test @cf/cloudflare/clairic against your validation datasets to compare accuracy and cost. Implement confidence-based routing: automate high-confidence extractions and send low-confidence results to review. For multi-step calculations or aggregations, extract the input values with Clairic and perform the arithmetic in your application code rather than relying on the model.
Model-reported confidence 85% (not measured accuracy)
Primary source ↗
written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
+## Workers AI - Introducing Clairic: an extraction model for typed values, now on Workers AI +https://developers.cloudflare.com/changelog/post/2026-10-19-clairic-workers-ai/ +Mon, 19 Oct 2026 00:00:00 GMT + +@cf/cloudflare/clairic is now available on Workers AI as a preview. Clairic is the first extraction model: a System One model that answers with values instead of text. We intend to release the model with open weights soon. +Decision models such as Clef choose among options you define up front. Many structured-output tasks do not have answers you can list in advance: an invoice total, a delivery date, the number of days a shipment is late, or what a repair will cost. Clairic handles these. You send a state and a schema of typed fields, and it returns one typed value per field. A value is read from the input, computed from it, or predicted beyond it. +Clairic does not generate tokens. It reads your input in one pass and decodes each answer under the rules of its type, so every answer is a valid value of the type you asked for, or null when the input does not determine it. +Typed fields +Define as many fields as you need. Fields that do not fit beside the input in one pass are split across parallel passes, so there is no upper limit. + +Type +Returns + +text +An exact span of the input, with its character offsets + +number +A number read or worked out from the input, honoring integer and decimals + +date, time, datetime +Real calendar dates and valid times, in ISO form + +duration +A length of time in the unit you choose + +list +Every matching text, number, or date, in input order + +estimate +A distribution inside your min and max, on your step grid, on a linear or log scale + +forecast +One estimate per future step of a series, up to 64 steps + +Every scalar answer includes p_null, the probability that the input does not determine the value, and a confidence score. Estimates and forecasts include a median and an 80% interval (p10 to p90). Set options.include_quantiles to also get all 99 percentiles. Use these to decide what to automate and what to send to review. +You can also pass up to four images alongside the state. +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" }, +issued: { type: "date" }, +due_date: { +type: "date", +instructions: "Issue date plus the net payment days", +}, +total: { +type: "number", +decimals: 2, +unit: "USD", +instructions: "Amount due including shipping", +}, +contacts: { type: "list", items: "text" }, +}, +}); + +// response.answers.invoice_number.value -> "INV-2291", with its span in the state +// response.answers.total.value -> the amount due, with p_null and confidenceconst 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" }, +issued: { type: "date" }, +due_date: { +type: "date", +instructions: "Issue date plus the net payment days", +}, +total: { +type: "number", +decimals: 2, +unit: "USD", +instructions: "Amount due including shipping", +}, +contacts: { type: "list", items: "text" }, +}, +}); + +// response.answers.invoice_number.value -> "INV-2291", with its span in the state +// response.answers.total.value -> the amount due, with p_null and confidence +Preview +The current endpoint is an early checkpoint, and we expect it to improve: + +Arithmetic: One- and two-step calculations, such as totals, differences, conversions, and date arithmetic, are reliable. Long chains of dependent steps and aggregations across many table rows are not yet. Extract the inputs with Clairic and do the math in code. +Estimates: Clairic estimates best when the input contains evidence such as comparables, history, or descriptive text. Without evidence, the interval is wide. +Forecasts: Forecasting is basic. Next-step forecasts follow recent patterns, but forecasts several steps out flatten toward the average, and Clairic does not anticipate events the series does not show, such as holidays. It does not replace a time-series model trained on your data. +Calibration: Intervals are trained to be calibrated and are on most held-out sets, but they can run narrow on unfamiliar data. +Confidence: Every answer is well formed, not necessarily correct. Use confidence, p_null, and the intervals to decide what to automate and what to send to review. +Dates: Dates without a year are resolved from context. If a field depends on the current date, set reference_date or add a line such as Today: 2026-10-19 to the state. + +Pricing +Clairic costs $0.10 per million input tokens. Because it generates no tokens, there is no output token charge. +Get started +Use Clairic through the Workers AI binding (env.AI.run()) or the REST API at /ai/run. You can also use AI Gateway with these endpoints. +For more information, refer to the Clairic model page, extraction models, pricing, and the blog post ↗︎.
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
| triage verdict | MATERIAL at 0.95, needed 0.5 |
|---|---|
| triage reasoning | New extraction model added to Workers AI with pricing and API surface changes. |
| signals | new model added to platform · new pricing tier introduced: $0.10 per million input tokens · new API capability: typed extraction with structured output · preview status with known limitations documented · new model identifier: @cf/cloudflare/clairic |
| suppression | — |
| triage model | anthropic/claude-haiku-4.5 ($0.00000) |
| writer model | anthropic/claude-sonnet-4.5 ($0.00000) |