d1-ultra from @LiquidAI is on AI Gateway. • #1# decision model on the Artificial Analysis Decision Index • Classify, route, and score text and images 𝚕𝚒𝚚𝚞𝚒𝚍/𝚍𝟷-𝚞𝚕𝚝𝚛𝚊

D1 from @liquidai is live on OpenRouter. It's a competitive decision model: send your app's state and yes/no, choice, or score questions, and get back typed answers with a probability for every option. Zero data retention. $0.04/M input, $0 output, 65K context

The new LFM 2.5 2.6B model by @liquidai is now available on iPhone and iPad. A fast model designed for edge devices with comparable or better scores compared to models up to nearly 4× its size. Update your app now.

The new LFM 2.5 VL 450M model by @liquidai is now available in the app. A lightning-fast and lightweight model perfect for image understanding in shortcuts. Update your app now.

I’m running a fully coherent model fully on my IPhone 15 pro max! LiquidAI LFM-2.6B in Q8 It did a web search and tool call and dropped facts. 22 tok/s prefill 2-3 tok/s decode But I could have used q4 for more speed

The same model, with the same weights, scores 62% in one agent harness and 33% in another. @adithya_s_k and the @huggingface team just released the ultimate guide to multi-harness RL, and it's one of the most practical RL write-ups this year, and everything open! The trick is simple. Don't touch the harness. Point it at a proxy instead of the model. The proxy speaks all four API formats coding agents use (OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, Gemini). It records the exact token ids and logprobs vLLM sampled, and you train on that. You don't change a single line of Claude Code, Codex or OpenCode. Results: 🔹 Trained across 4 harnesses at once, LFM2.5-2.6B by @liquidai went from 42% to 54% 🔹 31% fewer tool calls, thanks to a small bonus for solving tasks in fewer steps 🔹 Training in OpenCode alone took OpenCode from 34% to 58%, but the multi-harness model improved everywhere They also tried the shortcut everyone reaches for: fine-tune on 3,189 successful rollouts from Qwen3.8-27B. Imitation plateaued at 47.5%, below both RL runs. Copying a bigger model doesn't get you there. Practice does. The best part is that everything is open: the capture proxy in OpenEnv, the trainer in TRL, the tasks, the SFT data, the training code and all seven trained models. Agents will run in dozens of harnesses. Now open models can be trained for each of them, by anyone. Read it here 👇