Cloudflare's Clairic Targets Structured Data Extraction
A new multimodal model from Cloudflare focuses on turning documents and images into clean, structured output.
Cloudflare has published Clairic, a multimodal (vision-language) model aimed squarely at a practical problem: pulling clean, structured data out of messy inputs. Rather than chasing general chat benchmarks, the model is pitched for information extraction and structured output, according to its Hugging Face repository.
What it's for
Structured extraction is one of the least glamorous but most valuable jobs in applied AI. Enterprises routinely need to convert invoices, forms, screenshots, and scanned documents into predictable JSON or tabular records. A model tuned for that task can save teams from brittle regex pipelines and one-off OCR glue code.
Key points from the release:
- Clairic is a vision-language model, so it can reason over images alongside text.
- Its stated focus is structured output and information extraction rather than open-ended generation.
- It is distributed under a custom ("other") license, so teams should check the terms before production use.
The release leaves several technical details unspecified, including parameter count and context length, so prospective users will want to validate accuracy and throughput on their own documents before committing.
Why it matters
Cloudflare has been steadily building out its Workers AI platform, and an in-house extraction model fits neatly into that strategy. If Clairic performs well on real-world documents, it could give developers a lightweight, deployable option for turning unstructured media into usable data without stitching together multiple services.
Sources
- Visit
Cloudflare/clairic
Hugging Face
More from Cloudflare
All Cloudflare releases →Cloudflare's Clef brings structured decisions to open models
The new open-weight vision-language family outputs typed, structured results and arrives alongside a reinforcement-learning fine-tuning platform.
Cloudflare releases Clef open-weight decision models
The company pairs its new Clef family with a reinforcement-learning fine-tuning platform aimed at action-oriented tasks.
More in Vision-Language
All Vision-Language →SenseTime Releases Looped 9B Multimodal Model
The company's new SenseNova-Loop-9B pairs vision-language capabilities with a recurrent looped-transformer design.

Tencent releases Hunyuan Hy4-flash multimodal MoE
The lightweight, mixture-of-experts model adds vision and text instruction-following to Tencent's open Hunyuan lineup.

Thinking Machines releases Inkling 2 Mini, a compact open MoE
The Apache-2.0 multimodal model uses a mixture-of-experts design aimed at running locally rather than in the cloud.
0 comments
No comments yet. Be the first to weigh in.