Liquid AI d1
Liquid AI's hosted decision model (d1:free) that returns calibrated probabilities with zero output tokens for ticket routing, moderation, scoring, and reranking.
Why it matters
First decision model to beat Jev on Hugging Face's Decision Index — and available through OpenRouter's Decisions API, making structured decisions a one-line API call.
What you could build with it
A SaaS team drowning in support tickets could point d1's choice primitive at their inbox: each message gets a billing/technical/sales probability in one call with zero output tokens, replacing a chain of LLM classification calls and providing a confidence threshold for auto-escalation.
Does it hold up?
Too early to judge on independent evidence: vendor claims top Decision Index scores, but the model is API-only with no downloadable weights, so third-party evaluation is limited to hosted calls.
Built with Liquid AI d1
- D1 on OpenRouter: pricing and providersopenrouter.ai · Live provider page: $0.04 per million input tokens, $0 output, 65K context, 0.36s P50 latency, with public apps and token-volume activity showing real production use.
- Liquid AI's d1 model skips text, returns pure probabilitiesaidailypost.com · Launch writeup covering the three primitives and the d1:free hosted tier, with a caution that calibration claims deserve independent stress-testing.
Learn more
First spotted on article: 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 0.71Mistral 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 0.69DeepSeek 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 0.69kev: 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.