Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 18 additions & 0 deletions api-reference/models/d1-1.mdx
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
---
title: "d1.1"
sidebarTitle: "d1.1"
description: "Model details for d1.1. LiquidAI's decision model, answering named questions about a state on System One."
openapi: "api-reference/openapi/playgrounds/d1_1.openapi.json POST /systemone"
---

<Note>
This model is routable only on `/v1/systemone` (see
[System One](/api-reference/systemone)). Send the content to judge as
`state` — a string, an object, or an array — and up to 16 named `questions`
about it. It does not chat, stream, or call tools, so it 400s on
`/v1/responses` and `/v1/chat/completions`.
</Note>

> LiquidAI's d1.1 is a decision model and the successor to d1. Send a state — text, JSON, or images — together with several named questions, and every question is answered in a single forward pass: `noul` returns the probability of yes, `choice` picks one of your named options with a confidence and the full probability distribution, and `score` rates the state on 2 to 10 ordered levels. It generates no text, so output tokens are always 0 and only the input is billed, across a 65,536-token state. It is built for intent classification, agent routing, moderation, commercial-intent detection, triage, and LLM-as-a-judge checks, and it does not chat, stream, or call tools.

**References:** [Terms](https://www.liquid.ai/terms-conditions) • [Privacy](https://zerogpu.ai/privacy-policy)
Loading