Cloudflare releases Clairic extraction model for Workers AI
MarkTechPost: Cloudflare Releases Clairic, a System One Extraction Model on Workers AI
Cloudflare has released a preview of Clairic, a new System One extraction model on Workers AI. The Cloudflare Clairic extraction model reads text or images and returns typed values, not generated text. It targets a job developers usually give to LLMs: pulling totals, dates and IDs into JSON. Clairic answers every requested field in 1 forward pass, with no reasoning and no output tokens. TL;DR Size: Parameter count not disclosed. 65,536-token context window, up to 4 images per request.
What happened
Cloudflare has released a preview of Clairic, an extraction model designed to pull specific typed values like totals, dates, and IDs from text or images and return them as structured data. Unlike large language models that generate free-form text, Clairic answers all requested fields in a single forward pass without generating output tokens. The model is available through Workers AI at a cost of $0.10 per million input tokens with no charge for output tokens.
What each outlet adds
- MarkTechPost ↗: In Cloudflare's testing, the extraction step completed in 0.46 seconds compared to 16.1 seconds for a competing system, and when used in a multi-step pipeline reduced overall processing time by about 3.2x and costs by 49 percent.
- The Decoder ↗: Clairic can handle simple calculations, estimates, and forecasts, and is designed to work as part of larger processing chains where it extracts structured data before other models handle subsequent tasks.
Why it matters
Clairic addresses a common developer task of extracting specific values from documents, doing so faster and more cost-effectively than using large language models. The model enables more efficient multi-step document processing pipelines by specializing in data extraction rather than text generation.
Get smart on it
Cloudflare has released a preview of an extraction model called Clairic that pulls specific typed values like totals, dates, and IDs from text or images and returns them as structured data rather than generated text. Unlike large language models that generate free-form responses, Clairic completes extraction tasks in a single forward pass by answering all requested fields at once, with each answer including a confidence score and probability assessment. In Cloudflare's testing, the extraction step completed in 0.46 seconds compared to 16.1 seconds for a competing system, and when used as part of a multi-step pipeline with decision and text-generation models, reduced overall processing time by about 3.2x and costs by 49 percent. The model is available as a preview through Workers AI at a cost of $0.10 per million input tokens with no charge for output tokens.
Relevant courses
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on MavenRelated news
Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time
Mistral AI launched Voxtral 3, a new family of language models built for real-time voice agents. The system combines speech-to-text, text-to-speech, and a voice agent SDK, supports more than 50 languages, and lets agents tap into external tools during live conversations. It can run on your own infrastructure or through EU-hosted APIs to keep data under your control. The article Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time appeared
Voxtral 3
Voxtral 3: Mistral's voice agent SDK for real-time speech in 50+ languages — accurate transcription, emotional TTS, deep tool use. EU-hosted or self-deployed.
DeepSeek Open-Sources DeepInfer, the Inference Framework Behind DeepSeek-V4.1-Flash
DeepSeek has open-sourced DeepInfer, the inference framework that runs its production services. The DeepSeek DeepInfer inference framework is the engine behind DeepSeek-V4.1-Flash. It ships under the Apache 2.0 license. DeepSeek also released deepseek-recipe, its MIT-licensed token encoding and decoding layer. For developers, this is a rare look at a frontier lab’s real serving stack. TL;DR Size / scope: 1 supported model (DeepSeek-V4.1-Flash), 1M-token context window per the model
Also reported by The Decoder and SiliconANGLE
Nvidia launches new open models to run agents in the enterprise and on PCs
Nvidia is leaning hard into the trend of enterprise companies wanting to run their own open models in their own data centers and also trying to make on-device, private AI agents a thing.
Meta and Apple team up to make Muse AI models run better on Macs
The new Muse Spark Open AI model can work on M5 Ultra Mac Studios. | Photo: Amelia Holowaty Krales / The Verge Meta announced the Muse Spark Open AI model today, claiming that it's the "most capable US open-weight model to date." But the company also says that it's the "the first model in its class" that can "run on your desktop using two Apple M5 Ultra Mac Studios with the latest MLX framework." Meta and Apple, typically rivals, worked together on the launch and are publicly su
Also reported by The Decoder, TechCrunch, SiliconANGLE and MarkTechPost
Elevenlabs releases two new speech-to-speech models designed for real-time AI conversations
Elevenlabs' new Eleven Realtime speech-to-speech models combine speed and accuracy. The v1 Max variant scores 98.8 percent on the Big Bench Audio benchmark with a 0.57-second response time. Elevenlabs says no model on the Artificial Analysis leaderboard is both faster and more accurate. The article Elevenlabs releases two new speech-to-speech models designed for real-time AI conversations appeared first on The Decoder.