Ratings and Reviews 0 Ratings

Total 0 out of 5 stars
ease 0 out of 5 stars
features 0 out of 5 stars
design 0 out of 5 stars
support 0 out of 5 stars

This software has no reviews. Be the first to write a review.

Write a Review

Ratings and Reviews 0 Ratings

Total 0 out of 5 stars
ease 0 out of 5 stars
features 0 out of 5 stars
design 0 out of 5 stars
support 0 out of 5 stars

This software has no reviews. Be the first to write a review.

Write a Review

Alternatives to Consider

  • LM-Kit.NET Reviews & Ratings
    4.8 out of 5 stars 29 Ratings
    Company Website for LM-Kit.NET
  • SKU Science Reviews & Ratings
    4.6 out of 5 stars 16 Ratings
    Company Website for SKU Science
  • LTX Reviews & Ratings
    4.4 out of 5 stars 182 Ratings
    Company Website for LTX
  • Sogolytics Reviews & Ratings
    4.7 out of 5 stars 869 Ratings
    Company Website for Sogolytics
  • QEval Reviews & Ratings
    4.5 out of 5 stars 69 Ratings
    Company Website for QEval
  • D&B Credit Insights Reviews & Ratings
    4.2 out of 5 stars 70 Ratings
    Company Website for D&B Credit Insights
  • Canditech Reviews & Ratings
    5.0 out of 5 stars 111 Ratings
    Company Website for Canditech
  • D&B Connect Reviews & Ratings
    4.1 out of 5 stars 189 Ratings
    Company Website for D&B Connect
  • LeaseAccounting.app Reviews & Ratings
    Company Website for LeaseAccounting.app
  • SearchUnify Reviews & Ratings
    4.5 out of 5 stars 150 Ratings
    Company Website for SearchUnify

What is d1.2-ultra?

d1.2-ultra is a specialized multimodal artificial intelligence model developed by Liquid AI to perform structured decision-making, classification, extraction, and evaluation tasks. The model is designed to analyze input information and return specific answers with associated probabilities rather than producing open-ended natural language responses. Its omnimodal architecture supports text, images, and audio, enabling applications to process documents, photographs, recordings, and other unstructured information. Developers can use the model to answer Boolean questions, select classifications from predefined categories, assign numerical scores, and identify multiple applicable labels. Advanced information extraction capabilities allow d1.2-ultra to retrieve text, numbers, and dates from documents while identifying the exact source passages supporting its answers. The model can also detect sensitive personal information, identify every occurrence of specified text patterns, and indicate when requested information is missing. Its computer vision capabilities include locating objects using bounding boxes, identifying multiple instances within images, and estimating object counts with numerical confidence ranges. Audio processing supports spoken language recognition, environmental sound classification, and voice-based question inputs for multimodal decision workflows. Liquid AI reports that d1.2-ultra achieved 75 points on the Artificial Analysis Decision Index v2.1, with strong probability calibration that helps organizations establish reliable thresholds for automated decisions and human review. Available through the Liquid API at $0.042 per million input tokens, d1.2-ultra enables businesses and developers to build cost-efficient solutions for intelligent document processing, automated inspections, data classification, and operational decision support.

What is Perplexity Decider?

Perplexity Decider represents an advanced decision-making model featuring 27 billion parameters, evolved from Qwen3.8-27B, and is designed specifically for structured classification and multimodal decision-making tasks. Rather than generating freeform text, it evaluates an input state alongside a predefined decision schema to present the selected outcome along with calibrated probabilities. This model excels in making choice decisions from established categories and also handles noul decisions, assessing the probability of a yes-or-no answer. Additionally, it can analyze images in combination with text, allowing it to make well-informed decisions based on visual inputs such as screenshots. Common use cases involve routing support requests to the correct departments, like billing, technical support, or sales, and determining whether a message conveys urgency. With an overall accuracy rate of 85.71% across 11 diverse benchmarks, including FinancialPhraseBank, RAGTruth, JudgeBench, TabFact, ContractNLI, Circa, Belebele, and TruthfulQA binary, Perplexity Decider illustrates remarkable versatility and effectiveness in various decision-making environments. This significant accuracy level not only highlights the model's capabilities but also points to its potential for improving automated systems that require a nuanced understanding of both text and images, paving the way for future advancements in decision-making technologies.

Media

No images available

Media

Integrations Supported

Integrations Supported

Perplexity Decisions API
Qwen3.8-27B

API Availability

Has API

API Availability

Has API

Pricing Information

$0.042 per 1M tokens (input)

Pricing Information

Free
Free Version

Supported Platforms

SaaS

Supported Platforms

SaaS

Customer Service / Support

Not specified

Customer Service / Support

Web-Based Support

Training Options

Documentation Hub

Training Options

Documentation Hub

Company Facts

Organization Name

Liquid AI

Date Founded

2023

Company Location

United States

Company Website

www.liquid.ai

Company Facts

Organization Name

Perplexity

Date Founded

2022

Company Location

United States

Company Website

huggingface.co/perplexity-ai/pplx-decider-v1-27b

Categories and Features

AI Decision Models

Not specified

Categories and Features

AI Decision Models

Not specified

Popular Alternatives

GPT-6 Luna Reviews & Ratings

GPT-6 Luna

OpenAI
5.0 out of 5 stars

Popular Alternatives

Clef-flash Reviews & Ratings

Clef-flash

Cloudflare
d1.2 Reviews & Ratings

d1.2

Liquid AI
Clef Reviews & Ratings

Clef

Cloudflare
Jev Reviews & Ratings

Jev

TypeSafe AI
d1.2-ultra Reviews & Ratings

d1.2-ultra

Liquid AI