# Liquid AI's d1.2 and d1.2-ultra are now available on AI Gateway

Source: [Vercel](https://vercel.com/changelog/liquid-ais-d1-2-and-d1-2-ultra-are-now-available-on-ai-gateway)  
Feed7 permalink: https://feed7.dev/p/liquid-ais-d1-2-and-d1-2-ultra-are-now-available-on-ai-gateway-1rqgshb  
Published: 2026-11-19T00:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

Liquid's d1.2 models return structured decisions for audio and image inputs, including probabilities, category choices, scores, and bounding boxes. The faster, lower-cost d1.2 and more accurate d1.2-ultra offer a distinct option for classification tasks.

## Source Summary

**d1.2** and **d1.2-ultra** are available on AI Gateway with audio input and bounding-box support. Their Decisions API returns Boolean probabilities, category choices, rubric scores, or object boxes; multiple questions can use one input.

## Practical Implication

Use these models when an agent needs a structured decision, such as classifying a voicemail or locating an object in an image, rather than generated prose. Vercel's audio example requires **AI SDK 7.0.136 or later**.

## Agent-Ready Context

**d1.2** and **d1.2-ultra** are available on AI Gateway with audio input and bounding-box support. Their Decisions API returns Boolean probabilities, category choices, rubric scores, or object boxes; multiple questions can use one input.

Use these models when an agent needs a structured decision, such as classifying a voicemail or locating an object in an image, rather than generated prose. Vercel's audio example requires **AI SDK 7.0.136 or later**.

d1.2 is described as faster and lower-cost, while d1.2-ultra is described as more accurate. Decision requests appear in Gateway logs and count toward budgets; the material gives no comparative measurements.

## Connected Context

Feed7 judgment across 1135 accumulated Signals:

This adds audio input and object bounding boxes to the Gateway’s structured-decision options, extending beyond the classification and scoring use cases described for Gemini Decision 1 and Decision-1.1. It also makes the tradeoff between d1.2 and d1.2-ultra explicit, but supplies no measurements to validate it; audio use requires AI SDK 7.0.136 or later.

- [Gemini Decision 1 now available on AI Gateway](https://feed7.dev/p/gemini-decision-1-now-available-on-ai-gateway-0i56m75) — Both expose non-generative decisions through AI Gateway; this target specifically adds audio and bounding-box support, while Gemini Decision 1’s input support varies by API.
- [Decision-1.1 now available on AI Gateway](https://feed7.dev/p/decision-1-1-now-available-on-ai-gateway-14vmx9x) — Both provide structured Boolean, category, and score outputs. This target adds audio and object-box decisions, while Decision-1.1 emphasizes probabilities and compatibility with Decision-1 requests.
- [Jev is the fastest-adopted model in AI Gateway history](https://feed7.dev/p/ai-gateway-jev-model-launch-0rvbmm3) — Both concern typed decisions usable in agent control paths. The target specifies audio and image decision types, while Jev is framed for routing and guardrails; neither supplied record establishes comparative performance.

## Context Map

- Layer: model
- Domains: audio, image
- Topics: model-selection, tool-use

## Uncertainty

- d1.2 is described as faster and lower-cost, while d1.2-ultra is described as more accurate. Decision requests appear in Gateway logs and count toward budgets; the material gives no comparative measurements.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.
