Inception Mercury Decide: structured decision model via the System One Decisions API
Inception AI released Mercury Decide, a structured decision model that takes a state plus typed yes/no, choice, and score questions and returns calibrated probabilities (not text), served free on OpenRouter via the alpha Decisions API.
Why it matters
Joins OpenAI's Decisions API and Upstage Solar Decide in making 'decision models' — models that return probabilities instead of tokens, with output tokens free — a real product category; the free tier lowers the barrier to zero.
What you could build with it
A logistics company builds a dispatch assistant that scores candidate delivery routes and returns calibrated pick probabilities instead of text explanations, resulting in faster, auditable routing decisions at thousands of calls per minute.
Does it hold up?
Early but usable: served on OpenRouter with a free tier (32k context, zero token cost) through the Decisions API; independent analysis notes the calibrated probabilities still need validation on labeled holdouts before consequential use.
Built with Inception Mercury Decide
- digitalapplied: Decision Models — AI That Returns Probabilities, Not Textarticle · Independent Oct 1 route census covering Mercury Decide's free System One endpoint alongside OpenAI's Decisions API and Together's Tev1, warning that not all share one API contract or confidence guarantee.
Learn more
Mercury Decide on OpenRouter →
First spotted on x: source.
More AI models
ElevenLabs Eleven v4 + v4 Turbo: new emotive TTS architecture with a 100ms real-time variantElevenLabs released Eleven v4 and Eleven v4 Turbo on September 28: a new text-to-speech architecture with inline…models · JEV 0.72VoiceStudio: open-source, fully-local ElevenLabs alternative with voice cloning, dubbing and dictation in 646 languagesVoiceStudio is an open-source, fully-local voice AI studio: voice cloning from a 3-second sample, voice design, video…models · JEV 0.71DeepSeek V4-Flash official API: public beta with upgraded agent capabilities, Responses API and Codex supportDeepSeek's official V4-Flash is now a public beta API with massively upgraded agent capabilities - benchmark scores…models · JEV 0.69Mistral Forge: enterprise platform for training and continuously improving proprietary modelsMistral AI launched Forge (Sep 28) — a full-lifecycle model training platform (pre-training, SFT, DPO/ODPO, RL…models · JEV 0.69kev: open, trainable Jev-like family of small decision models on Qwen3.5/3.8A family of small decision models (0.8B to 27B) built on Qwen3.5/3.8 that reproduces Jev's prefill-only typed-decision…models · JEV 0.68GPT-Synopsys: OpenAI and Synopsys multi-year deal to build an AI model that operates EDA toolsOpenAI and Synopsys signed a multi-year agreement on Sep 30 to jointly develop GPT-Synopsys, a specialized model that…models · JEV 0.66
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.