Change language to
0:00

Cloudflare has released two open-weight Clairic models that turn receipts, PDFs, and text into structured data.

The models are a developer tool, not a consumer app. Extraction means turning receipts, PDFs, or text into named fields such as supplier, line items, and total. The smaller Clairic-flash costs $0.10 per million input tokens on Workers AI, and Unite.AI reports developers can also run it on their own hardware.

Cloudflare's Clairic model turns a receipt and PDF pages into structured data. (image 2)
Image: Cloudflare

Cloudflare’s 18 November release pairs the updated, 27-billion-parameter Clairic with the new 9-billion-parameter Clairic-flash. Both are hosted on Workers AI, and the full weights are on Hugging Face.

Subscribe to our Newsletters for more Tech Stories

What’s changed since the October preview

The October preview was a hosted endpoint running the 9B model. The updated Clairic can now read PDFs and images, pulling the supplier, line items, and total in one request even when they appear on different pages. Each request can include up to four images or PDF pages in total.

Cloudflare's Clairic model turns a receipt and PDF pages into structured data. (image 3)
Image: Cloudflare

Cloudflare redesigned how the models fill ordinary text and number fields. Instead of producing them in a single pass, the models build each field step by step while working on multiple fields in parallel. Separate components handle estimates, forecasts, durations, calculated dates, and arithmetic.

The typed API still returns confidence scores, character spans, and probabilities. Cloudflare says customers asked for use cases from extracting data from receipts to reading values from support tickets.

Clairic vs Clairic-flash: accuracy and speed

There aren’t any public extraction benchmarks yet, so these are the company’s own internal evaluations, not independent results. Image-reading errors fell from 207 to zero in those tests.

Model or systemFresh text fields (96 requests)Tracked customer assertions (139 request shapes)Synthetic receipt fields
Clairic preview295/3361,033/1,263369/576
Clairic (27B)335/3361,263/1,263576/576
Clairic-flash (9B)328/3361,263/1,263576/576
D1.2 + OCR304/336973/1,263397/576
ScaleDown259/336653/1,263280/576

Clairic-flash matched the larger model on the customer assertions and synthetic receipts, but got seven fewer fresh text fields right. It was faster in all six latency tests. The timings below are Cloudflare’s own measurements from its self-hosted server, not independent benchmarks.

WorkloadClairic median / 95th percentileClairic-flash median / 95th percentile
Fresh text fields358 / 736 ms155 / 328 ms
Fresh image fields453 / 976 ms305 / 605 ms
Commercial leases691 / 803 ms379 / 519 ms
Loan pricing395 / 407 ms188 / 192 ms
Traffic forecasting532 / 585 ms243 / 261 ms
Expense audit632 / 742 ms393 / 512 ms

Workers AI pricing and how to run Clairic locally

ModelWorkers AI endpointStandard price per million input tokens (USD)
Clairic (27B)@cf/cloudflare/clairic$0.24
Clairic-flash (9B)@cf/cloudflare/clairic-flash$0.10

Both models cost $0.10 per million input tokens until 1 December 2026, after which the 27B model returns to $0.24. Workers AI doesn’t charge for output tokens.

Existing apps on the preview Clairic endpoint automatically move to the updated model without an API schema change. The 9B option now has its own Clairic-flash endpoint and keeps the preview’s $0.10 rate.

Unite.AI says developers can run the models locally with PyTorch and Transformers without using Workers AI. Both Hugging Face repositories use the Apache-2.0 licence and include weights, typed-output components, tokeniser and processor files, and Python helpers.

Cloudflare also introduced its Workers AI Superintelligence research team, which built Clairic and Clef. The company bought Deno in October, and Tbreak covered Deno’s programming model.

Until 1 December, both models cost $0.10 per million input tokens. After that, the 27B model’s $0.24 rate applies, 2.4 times the Clairic-flash price.