Clairic: Cloudflare's System One extraction model that writes no output tokens
Cloudflare announced Clairic on Oct 19, a preview on Workers AI (@cf/cloudflare/clairic) and the first model in its new 'System One extraction' class: it extracts, computes, estimates and forecasts typed values in a single forward pass with zero output tokens. Priced at $0.10 per million input tokens with a 65,536-token context, open weights promised later.
Why it matters
A purpose-built model for the structured-extraction calls that teams currently burn frontier LLM tokens on: typed values with confidence scores and null answers, single-pass, billed on input only.
What you could build with it
A developer automating invoice or insurance-claim processing could route each field-extraction step (invoice total, due date, line items) through Clairic on Workers AI, replacing one LLM call per document with a single typed pass and escalating only low-confidence fields to a frontier model.
Does it hold up?
Too early to judge: preview only, released Oct 19. Cloudflare's own pipeline numbers are promising but untested outside their claims pipeline, and weights are not public yet.
Built with Clairic
- Unite.AI: Cloudflare releases Clairic, its first System One extraction modelarticle · Overview of the preview release: single forward pass extraction, no output tokens, Workers AI REST and env.AI.run() access, open-weights release planned.
- ppc.land: Clairic cuts AI pipeline cost 49% in Cloudflare's own testarticle · Breakdown of Cloudflare's damage-claims pipeline test (Clairic + Clef vs GLM-5.3 alone: 49% cheaper, 3.2x faster) plus acknowledged weak spots in multi-step arithmetic and forecasting.
- dev.to: Clairic writes no output tokens - read value, not guessarticle · Developer-oriented explainer on wiring up @cf/cloudflare/clairic: typed field maps, 8,192-token field+input budget per pass, embedded-image support, AS-IS preview terms.
Learn more
First spotted on article: source.
More AI models
OpenAI publishes 722 AI-generated math manuscripts from an unreleased modelOpenAI released 722 mathematical manuscripts in 372 result families to GitHub under Apache-2.0, produced by an…models · JEV 0.74Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73NVIDIA Isaac Lab 3.0 GA + Isaac OS open runtime + Agile ONE SN humanoidMajor Isaac platform expansion at GTC Berlin Oct 21: Isaac Lab 3.0 is generally available as the open-source robot…models · JEV 0.73StepFun Step-5-Preview — open BF16 weights releasedStepFun published the full BF16 weights for its flagship Step-5-Preview agentic model (600B-parameter sparse MoE, 27B…models · JEV 0.73NVIDIA Nemotron 3.5 Retriever collection: Embed 8B/1B, Rerank 8B, Parse 631MNVIDIA's Oct 21 collection drop for agentic retrieval: Nemotron-3.5-Embed in 8B BF16, 1B BF16 and 1B NVFP4…models · JEV 0.72Kimi K3.1 Pro: Moonshot's 2.8T open-weight flagship officially launchesMoonshot AI officially launched Kimi K3.1 Pro on Oct 23, a mixture-of-experts model with 2.8 trillion total / 104…models · JEV 0.72
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.