As of: 2026-10-20 07:28 CEST.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/clairic/

# Clairic

Cloudflare. Status: preview. Type: language model. Released: 2026-10-19. Training cutoff: not published.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Cloudflare Workers AI | `@cf/cloudflare/clairic` |  | https://blog.cloudflare.com/clairic-extraction-model/ |

## Pricing

- Price not published.
- Last checked: 2026-10-20

## Specs

- Input: text
- Output: text
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## What it has not seen

- No published training cutoff. Counted from its release (2026-10-19): at least 2 AI events since (0 major, 0 historic), as of 2026-10-20.
- Everything since September 2026: https://postcutoff.com/since/2026-09/

## What stands out

- Non-generative extraction with confidence scores: Reads input in a single forward pass and returns typed values, character-offset spans, null probabilities and confidence scores for extracted, computed, estimated or forecast fields, without generating output tokens. Source: https://blog.cloudflare.com/clairic-extraction-model/

## Notes

Preview. Billed on input tokens only (rate not published in the launch post). No parameter count or standard benchmarks; Cloudflare says open weights are coming "soon". Output is structured values, not free text.

Call it from a Worker with `env.AI.run("@cf/cloudflare/clairic", ...)` or through the Workers AI REST API.

Source: [Cloudflare blog](https://blog.cloudflare.com/clairic-extraction-model/)

Model page: https://postcutoff.com/m/clairic/