Skip to content
01

Providers + pricing

CapabilitiesProvider details
● Your own key · billed by your provider · AnyRouter fee $0
Liquid
liquid-byok
BYOK—
Unavailable
● Free pool · donated keys · not available for this model — donate a key
02

Try it

POST /api/v1/decisions

Decisions try-it

Full app
Compare1 / 4

Request

427 / 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?

Yes99%

request_typechoice

What is the primary request in this email?

custom_capacity78%confidence 81%

business_impactscore

How much business impact does this request have?

3.4/ 4between Launch-blocking and Revenue at riskconfidence 76%

507 in · 72 out tokens

POST /api/v1/decisions
Checking session…
03

Uptime + latency

—recent checks · all routes

No health checks recorded for this model yet.

24h
No traffic in the last 24h.
More performance detail
Usage analytics

Loading usage…

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.

Liquid d1

Also accepted:liquid/d1:free
  • Liquid
Decisionstate + questions → p32Ktoken context
Context
32K
Input
$0
Output
$0
TTFT
—
Uptime
—
Routes
1
04

Your access

Credits
Your own key · AnyRouter fee $0

Run Liquid d1 on your own key — your requests are billed by the provider. Pool callers pay AnyRouter credits.

No BYOK keys configured for this model yet.

Share a key with the pool to earn credits for every request it serves, covering your plan cost.

Free poolnot in pool yetDonate key →
Create API key for this model
Decisions
Context length32,000 tokens
ArchitectureTransformer
Categorytext
ReleasedSep 29, 2026
Modalities
Capabilities
05

About

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).

Released 2026-09-29 · params: state · model · questions

Share cards
Liquid d1 share card
Liquid d1
Liquid upstream share card
Liquid upstream
Back to models