---
id: "liquid/d1-ultra"
also: ["liquid/d1-ultra-20261015", "vercel/liquid/d1-ultra"]
card_usd_per_m: "0.042 in, 0.0 out, at liquid"
cheapest_list_usd_per_m: "0.042 in, 0.0 out, at liquid on openrouter"
cheapest_effective_usd_per_m: "0.0417 in, 0.0 out, at liquid on openrouter"
context: 32768
max_output: 29491
input: ["text", "image"]
output: ["decisions"]
released: "2026-10-15"
api: ["/api/alpha/decisions"]
params: ["max_tokens", "stop", "temperature"]
endpoints: 2
gateways: "openrouter (1), vercel (1)"
no_training: 1
trains: 1
retains_prompts: 1
---
# LiquidAI: d1-ultra

Liquid d1-ultra is a multimodal decision model for classification, routing, and scoring across text and images, with a 32,768-token context window. It returns calibrated probabilities for yes/no, multiple-choice, and scale-based questions in a single forward pass without generating output tokens. It is designed for demanding real-world tasks such as visual defect inspection and evaluating damage claims against customer photos.