explainx.ai350K+ learn from us
TrendingAI News TodayPathwaysSkills
Pricing
explainx.ai

Upskill in AI — 16 free pathways, live workshops & bootcamps, and 50+ courses from practitioners. Plus the skills, tools, and MCP servers to practice on.

follow us

follow on google

Add explainx.ai as a preferred source

corporate training

support@explainx.ai

get started

Find your pathTake Free Evaluation

community

Join the community

learn

mind: share how you thinkpathways — start freeworkshopsbootcampscoursescompare Explainxcertificationsmock testsexplainx universitycorporate traininglearn skills & mcp

discover

skillsmcp serversexplainx mcpestacktoolsmdx readeragentsllmsdesignsdictionarypeopleagi trackerfelony benchranks

company

aboutvisionmissionteaminstructorsteach on explainxpartnershipscommunityhackathonscareers

content

daily AI newsstate of AI — live resultsblogreleasespromptsgeneratorsresource libraryfor LLMsexplainx.ai kids

solutions

all solutionsdeveloper upskillingmarketing upskillingproduct manager upskillingleadership upskilling

newsletter · weekly

Get AI news, tools, and insights in your inbox.

supportcontactprivacytermsdata rightshow we create contentsubmission guidelines

© 2026 AISOLO Technologies Pvt Ltd

explainx.ai

On this page

  • TL;DR
  • Five new task types (what builders gain)
  • Audio: when it matters
  • Decision Index v2.1: claimed leaderboard
  • Calibration table (vendor numbers)
  • Sample accuracy rows Liquid published
  • When to pick d1.2 vs a chat model
  • Agent pipelines: where d1.2 slots in
  • Audio tasks in practice
  • Cost worked example (input-only billing)
  • Claimed vs verified checklist
  • How to try d1.2 today
  • d1.2 vs d1-ultra vs open d1 weights
  • How this fits the LFM3 family
  • What people are asking
  • Related on explainx.ai
  • Sources
  • Migration from d1-ultra and d1.1
  • Security and abuse considerations
← Back to blog

explainx / blog

Liquid AI d1.2: Audio, New Tasks, and Decision Index 75

Liquid AI, Decision Models, Models, API, Audio

Part of Decision Models

Liquid AI shipped d1.2 and d1.2-ultra on November 16, 2026 with audio input, five new decision tasks, and a 75 score on Artificial Analysis Decision Index v2.1. Pricing, API IDs, and how to try them.

Nov 16, 2026·8 min read·Yash Thakker
add explainx.ai
go deep
Liquid AI d1.2: Audio, New Tasks, and Decision Index 75

Liquid AI released d1.2 and d1.2-ultra on November 16, 2026, adding audio input, five new structured decision tasks, and a claimed 75 on Artificial Analysis Decision Index v2.1 for the ultra tier. The announcement is on Liquid's blog with API pricing $0.02 per million input tokens for d1.2 and $0.042 for d1.2-ultra.

If you only know chat models, decision models return calibrated probabilities for closed questions in one forward pass — no parsing assistant paragraphs. We explained the category in what are decision models and tracked d1-ultra's October launch. d1.2 is the task-and-modality expansion, not a new pricing philosophy.

TL;DR

table · 2 cols
QuestionAnswer
Release dateNovember 16, 2026 (Liquid blog)
Model IDsd1.2, d1.2-ultra on Liquid API
Price (input)$0.02/M (d1.2), $0.042/M (d1.2-ultra)
Index claim75 on Decision Index v2.1 (d1.2-ultra)
New inputsAudio (subject or spoken question)
New tasksValue read, spans, boxes, count+range, multi-select
EndpointPOST /decisions/v1/systemone (docs)
Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

Five new task types (what builders gain)

Liquid AI d1.2 multimodal decision task types illustrationLiquid AI d1.2 multimodal decision task types illustration Image: Liquid AI

Liquid's post lists tasks that usually require fragile regex or a full VLM chat loop:

  1. Read a value from invoices or forms — returns the value or not found instead of hallucinating.
  2. Span detection — find every PII passage with positions (Nemotron PII-style evals in their table).
  3. Box localization — one object or every instance in a photo (RefCOCO family).
  4. Numeric estimation — count with range (COCO-style counting).
  5. Multi-select choice — multiple topics true at once, each with probability.

Each type uses the same endpoint and request shape Liquid showed for d1-ultra, which lowers integration cost if you already run Mercedes on-device voice experiments or Amazon Bedrock decision screening.

Audio: when it matters

Audio support matters for safety and ops pipelines where sound is the signal:

  • Detect sirens, languages, or background machinery in field video.
  • Accept spoken questions when operators wear gloves on factory floors.

Liquid does not publish sample rate limits in the headline post; check Liquid API docs before you ship production MIME types.

Decision Index v2.1: claimed leaderboard

Artificial Analysis Decision Index v2.1 scores for d1.2-ultraArtificial Analysis Decision Index v2.1 scores for d1.2-ultra Image: Liquid AI

Liquid says d1.2-ultra hits 75 on Artificial Analysis Decision Index v2.1, two points above the prior best, and claims both models are best for their cost tier on that index.

Treat the index like any vendor-adjacent benchmark:

table · 3 cols
ClaimSourceIndependent check
Score 75Liquid blog Nov 16Reproduce via AA when public
+2 vs prior bestLiquid blogCompare to d1-ultra October post
Best cost curveLiquid blogPlot $/M input vs score yourself

Our Jev 1.14 guide and Phonic speech-to-speech index claims show how explainx.ai handles index-only launches — ship the how-to, flag unverified leaderboard lines.

Calibration table (vendor numbers)

Liquid AI d1.2-ultra calibration error comparison chartLiquid AI d1.2-ultra calibration error comparison chart Image: Liquid AI

Liquid publishes calibration error across 13 benchmarks and 22,505 questions:

table · 2 cols
ModelCalibration error (Liquid)
d1.2-ultra0.8
d1.21.2
Jev 1.142.7
Perplexity Decider v1.33.7
GPT-6 Luna (Decisions API)7.2

Calibration matters because threshold automation only works when 0.8 means ~80% correct. For compliance routing, pair calibrated scores with human review queues rather than blind auto-approve.

Sample accuracy rows Liquid published

table · 3 cols
Taskd1.2-ultrad1.2
Receipt value read (CORD, SROIE)98%96%
PII spans precision / recall94% / 93%92% / 88%
RefCOCO localization94%94%
COCO count within one93%92%

Run your documents — receipt layouts and camera angles differ from benchmarks.

When to pick d1.2 vs a chat model

Chat models excel at open-ended drafting. They are expensive and brittle when you only need yes/no with a score, one label from ten, or a count in a band. Decision models never generate prose, so you skip JSON repair and tool-parse failures.

table · 3 cols
JobChat model riskd1.2-style answer
Invoice totalInvents a numberValue read or not found
PII scrub checkMisses a phone in paragraph 3Span list with offsets
Warehouse photo QCLong caption, no boxesRectangles per defect
Support ticket routingOverconfident single tagMulti-select with probabilities

That pattern shows up in Cloudflare Clef-Omni and NACE Drex launches too — Liquid is pushing task breadth and audio as its differentiator this week.

Agent pipelines: where d1.2 slots in

A typical agent harness can call d1.2 as a cheap screen before an expensive frontier model runs:

  1. Ingest email, PDF, image, or audio clip.
  2. Ask structured questions (noul, spans, boxes).
  3. Branch on probability thresholds — auto-approve, escalate, or call a frontier chat model for synthesis only on low-confidence rows.

This is the same screening-layer idea as Bedrock AgentCore evaluations, but with Liquid-native pricing at two cents per million input tokens on the base tier.

Audio tasks in practice

Liquid gives two audio patterns:

  • Audio as state — the model hears the clip and answers typed questions (siren, language, machine noise).
  • Audio as question — operators ask aloud instead of typing.

For compliance, log whether spoken questions include PII before you send them to a cloud API. On-device LFM2.5-Audio may fit air-gapped lanes later; d1.2 is hosted API today.

Cost worked example (input-only billing)

Liquid bills input tokens only on decision models. If a 1024×1024 image costs 1,536 tokens (per d1-ultra docs) and you ask four questions, you pay roughly four prompts worth of input, not generated answer tokens.

At $0.02 per million for d1.2, one million image tokens of state is two cents before questions — attractive for high-volume triage if latency meets your SLA. Ultra at $0.042 is still far below frontier chat output pricing for the same workload, though you must accept closed-world questions.

Claimed vs verified checklist

table · 2 cols
ItemStatus Nov 16
Models live on Liquid APIStated on Liquid blog
Decision Index 75Vendor table; AA confirmation pending
Calibration 0.8 errorVendor table across 22,505 questions
Receipt 98% cellVendor benchmark row
OpenRouter / VercelLiquid says coming soon on Nov 16 post

Builders should run 50 real invoices before swapping production fraud rules — the same discipline we used for Liquid d1 vision.

How to try d1.2 today

  1. Create a key at console.liquid.ai.
  2. Call POST https://api.liquid.ai/decisions/v1/systemone with "model": "d1.2" or "d1.2-ultra".
  3. Pack state (text, images, or audio per docs) and typed questions matching Liquid's System One schema.
  4. Read probabilities from the response — no output token stream.

Liquid's post includes an invoice extraction example that asks for a missing fourth field to prove not-found behavior — copy that pattern when you unit-test agents that currently use GPT-6 Astra JSON mode.

d1.2 vs d1-ultra vs open d1 weights

table · 2 cols
TrackBest for
d1.2 APINew tasks + audio, lowest $0.02 tier for bulk triage
d1.2-ultra APIHighest index score in Liquid's table, same $0.042 ultra price
Open d1 on Hugging FaceEdge and on-device per open d1 guide

How this fits the LFM3 family

Liquid shipped LFM3 open multimodal 2B models in October. d1.2 is the decision-specific lane — smaller surface, probability outputs, input-only billing. Teams often pair LFM3 for drafting and d1.2 for gates.

What people are asking

Is d1.2-ultra worth 2.1× the d1.2 price?

Only if your error cost dominates API cost. Fraud, safety, and regulated PII flows often fit that math; bulk content moderation may not.

Will OpenRouter carry d1.2?

Liquid listed OpenRouter for earlier tiers; November 16 says OpenRouter and Vercel coming soon while Liquid API ships first. Watch Liquid models page for gateway badges.

Does this replace Claude or GPT for coding?

No. Decision models classify and score; they do not edit repos. Keep Claude Code for patches and d1.2 for pre-flight checks.

Related on explainx.ai

  • Liquid d1-ultra October launch
  • What are decision models
  • Open d1 edge weights
  • LFM3 multimodal family
  • Jev 1.14 comparison baseline
  • NACE Drex open decision models
  • Bedrock AgentCore decision screening

Sources

  • Liquid AI: d1.2 announcement (Nov 16, 2026) — primary.
  • Liquid API reference: Make decisions — primary.

Migration from d1-ultra and d1.1

If you pinned d1-ultra:latest, Liquid previously documented d1:latest aliases on the Make decisions endpoint. d1.2 adds task types your older schema may not send — audit question type enums before cutover.

d1.1 (October 30 on Liquid's news page) remains listed; d1.2 is the modality + task superset announcement. Teams on Jev or Perplexity Decider should compare calibration tables on identical holdout sets, not marketing index points alone.

Security and abuse considerations

Decision models can leak training biases into probability skew on demographic proxies in photos or audio. For HR and lending, keep human review on any auto-action and log model version (d1.2 vs d1.2-ultra) with each decision.

Span and box tasks can surface PII you intended to redact — treat model outputs as sensitive data in your vault, similar to ChatMate RPE lessons on exfiltration via assistant channels.

Accurate as of November 16, 2026. Index scores and benchmark percentages are Liquid's unless Artificial Analysis republishes them. Re-run benchmarks after each model pin change.

Spotted something out of date? Let us know.
Daily briefFrom Yash · 350K+ students taught

Catch up on AI

One AI story explained in plain English, plus one thing to try. Every day, free. Unsubscribe anytime.

  • ✓ Free
  • ✓ One email a day, no spam
  • ✓ Unsubscribe anytime
Yash Thakker

Written by

Yash Thakker

Yash is an AI expert with over 300K learners. Join his workshops →

View Yash Thakker in People in AI →

Related posts

Oct 15, 2026

Liquid AI d1-Ultra: A $0.042 Decision Model Claiming the Top Spot

Liquid AI released d1-ultra, a decision model that reads text and images and returns calibrated probabilities instead of text. Its blog claims it beats Jev 1.14 and all other models on a decision index by at least 8 points. We separate what Liquid says from what can be checked.

Nov 6, 2026

Nace AI Drex: Open-Weight Decision Models, and the Licence Catch

Nace AI has put its Drex decision models on open weights. Drex Max v1 is a dense 27B model that scores typed questions instead of writing prose. Here is what is confirmed, what is self-reported, and why "open source" is the wrong label.

Oct 9, 2026

Cloudflare Clef-Omni: An Open Multimodal Decision Model for Audio, Video and Images

Cloudflare added Clef-Omni to its Clef family of decision models: an open-weight 30B-A3B mixture-of-experts that reads text, images, audio and video and returns probabilities, not prose. Here is how it works, how it scores, and when to pick it.