Cloudflare bets you’re overpaying an LLM to read your invoices

Cloudflare released a preview of Clairic, an extraction model that pulls typed values out of messy text and images in one pass without generating tokens. In Cloudflare's test on a damaged-product support claim, a pipeline built around Clairic finished in 19.3 seconds versus 61.7 seconds for a version that used an LLM at every step, and cost 49% less. Clairic targets the extraction work developers routinely hand to large language models, such as reading invoices.

Cloudflare released a preview of Clairic, an extraction model that pulls typed values out of messy text and images in one pass without generating tokens. In Cloudflare’s test on a damaged-product support claim, a pipeline built around Clairic finished in 19.3 seconds, against 61.7 seconds for a version that used an LLM at every step, and cost 49% less. Clairic goes after a job developers routinely hand to large language models: read this invoice and … More https://www.helpnetsecurity.com/2026/10/20/cloudflare-ai-clairic-extraction-model/ The post Cloudflare bets you’re overpaying an LLM to read your invoices https://www.helpnetsecurity.com/2026/10/20/cloudflare-ai-clairic-extraction-model/ appeared first on Help Net Security https://www.helpnetsecurity.com .