Mouse-1: decision model for agent harnesses
Decision model for agent harnesses launched Oct 21 on Product Hunt by maker Pete McGrath. Optimized for the hundreds of small decisions an agent makes per task: takes the agent's state and options, returns a probability. Claims ~190x cheaper and 13x faster than Opus 5.5 with the same output, 163x cheaper and 65x faster than GPT-6 Sol. Single API endpoint, zero data retention, LoRA fine-tuning pass-through from the H100 provider at zero markup.
Why it matters
The cheapest seat in the agent-harness stack: a purpose-built decision/calibration model that claims the same harness output as Opus 5.5 at ~1/190th the cost, tunable per-harness with LoRA so it improves with use.
What you could build with it
An indie developer running a multi-agent coding setup could route all the small per-step decisions (tool choice, classification, routing) through Mouse-1's single endpoint and check whether the agent's total cost really drops 100x with no quality loss.
Does it hold up?
Too early to judge — launched Oct 21; all figures are the maker's own evals. The competitive set is small (Microsoft Decision-1, Jev) and independent comparisons don't exist yet.
Built with Mouse-1
- Mouse-1 launch thread (Product Hunt)producthunt · The launch thread itself: maker Pete McGrath describes the evals (~190x cheaper, 13x faster than Opus 5.5, same output) and LoRA fine-tuning pass-through.
Learn more
First spotted on producthunt: 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.