Skip to content

Liquid AI · Decision

d1.2-ultra

Liquid AI 🇺🇸Decision
From Aiml API's listing:
d1.2-ultra is Liquid AI's most capable decision model: instead of generating text it reads text and images and returns calibrated, typed answers in one forward pass with no output tokens — yes/no, one or several choices, a score, a value (text, number or date) or every passage of a kind read from the input, a box around one object or every instance in a picture, or a number estimated with a range. For harder classification, moderation, routing, extraction and visual inspection decisions, and LLM-as-judge checks.
Max context
66K
Listings
4
Providers
3

Evidence and sources

Maker HQ: US (source)
All rankings: #119 on OpenRouter today #163 on OpenRouter this week #259 on OpenRouter this monthSources: AI/ML API data, OpenRouter Decision Models data docsPrimary data from AI/ML API from OpenRouter Decision Models: name

Advantages and trade-offs

Compared with 10 representative decision models

Trade-offs

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

Inputs as stated by providers; output from the model’s type
Text
Images
Choices and scores

Capabilities

Supported operations and provider-stated features

DecisionExtractionVision

Listings

 OpenRouterInference by LiquidNo output chargeliquid/d1.2-ultraSource: OpenRouter Decision Models data docs66K$0.042225ms
 OpenRouterNo output chargeliquid/d1.2-ultraSource: OpenRouter Decision Models data docs66K$0.042—
 VercelNo output chargeliquid/d1.2-ultraSource: Vercel AI Gateway data66K$0.042—

1 listing without a price is hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Other

Around the web

Also known as: liquid/d1.2-ultra

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works