lets find a new one shall we

You already gave the LLM the answer. So why is it writing it out from scratch? Introducing a new AI model architecture: Constrained Decoding Models (CDMs) LLMs were built to write. Most production workloads just need an answer: fast, consistent, and affordable. CDMs are purpose-built for 1 task each. They read your input once and skip the token-by-token generative loop that makes LLMs slow and expensive. Not just a decision model, but a family of 3 CDMs live today: • Classify: define your labels and get back a calibrated probability + reason for each. Used for routing, tagging, and intent detection. • Extract: describe the entities in natural language and get back well-formed JSON with confidence scores + citations. Used for web scraping, document processing, and PII redaction. • Summarize: pass in long text, images, or PDFs and get back a consistent summary under 1,000 tokens. Used for context compaction, metadata generation, and transcript digests. Built for production: • 1M tokens of multimodal (text + image) input, 31x larger than Jev • 77.2% on DecisionBench vs Jev's 72% • 200x faster, 467x cheaper than frontier LLM APIs • $0.05/M input tokens. Output is free (yes, even for summarize) Live on your favorite platforms today: @OpenRouter @vercel_dev @LiteLLM @LangChain @TrustedRouter @itsArthurAI @useRouterPlus Get 50M input tokens for free (for the first 50 hours) at link below 👀

Introducing Anatomy Describe a machine in one line. Claude brings it to life. - Interactive isometric wireframes you can rotate, inspect and explore - WebGL shaders for fire, water, plasma and more - Real 3D motion, with individual parts that rotate and move Install it as an agent skill. Fully open source.

Jev is a super fast video editor! Edited this entire video in less than a minute, and here's how: First, I transcribed raw vid locally with word timestamps, cut it into 16 beats, then asked Jev these seven questions about every beat: does this line need a visual at all? which card template? (18 to pick from, premade) which text effect? which transition into it? how hard do we punch in on the face? which sound effect? which word gets emphasised? Plus five about the video as a whole. Style, colour, caption treatment, energy, progress bar. 117 questions answered by jev < 1 s ~ $0.0017 Using @typesafeai via @LiteLLM

meet @LiteLLM Lens, the next era of tracing and self improving agents. • stop reading traces. let Lens investigate them • get bug fixes and feature requests right in Slack • see the evidence, replay the failures, measure the improvement

We’re rolling out monthly Claude Platform API credits for Max and Team plans: Max 5x: $100 Max 20x: $200 Team: up to $500, pooled Works on any model, including Haiku 5.5, in your code or third-party harnesses. How it works and full terms: support.claude.com/en/articl…

We're open-sourcing Moyai, the cloud coding agent our team uses every day It works with Claude Code, Codex, OpenCode and runs on 100+ providers through @LiteLLM Before our Devin bills were $101,872 with Moyai we're now at $21,700 (79% less)

New @LiteLLM Lens update: datasets. If you're building agents with Lens, the loop is now: 1. Lens finds your failing traces 2. You add them to a dataset 3. You run evals on your agents