Liquid d1

Also accepted:liquid/d1:free

Liquid d1 is Liquid AI's first decision model: send application state and typed questions (noul / choice / score) and get calibrated probabilities back in a single call with zero generated tokens — not chat text. Built for classification, routing, scoring, moderation and guardrails. Call POST /api/v1/decisions (POST /api/v1/systemone is the same handler).

Providers

ZDRUnavailable

			Capabilities
Liquid liquid-byok	$0	$0	Unavailable

Decisions try-it

Full app

Request

State427 / 12,000

Typed questions

requires_replynoul
request_typechoice
business_impactscore

liquid/d1

Sample

requires_replynoul

Does this email require a human response from AnyRouter support?

NoYes

99%

request_typechoice

What is the primary request in this email?

Selectedcustom_capacity

custom_capacityA custom capacity or pricing commitment

78%

enterprise_planPlan, contract, or account options

12%

rate_limitHigher request, token, or throughput limits

account_bugA broken account, key, dashboard, or API behavior

confidence 81%

business_impactscore

How much business impact does this request have?

3.4 / 4between Launch-blocking and Revenue at risk

No impact

Minor

Material

Launch-blocking

42%

Revenue at risk

47%

confidence 76%

507 in · 72 out tokens

POST /api/v1/decisions

Checking session…

Usage analytics

Loading usage…

API & code

Decisions API

/api/v1/decisions

Typed decisions (noul, choice, score).

Uptime & Health

No uptime data yet

These providers haven't been health-probed for this model yet. The router still routes around upstreams that fail live requests — uptime fills in once probe history accrues.

Share cards2 images