d1 overview
d1 by Liquid AI
d1 returns typed decisions with calibrated probabilities, not text. Available on AI/ML API via the /v1/decisions endpoint.
d1 specs
- Model ID
liquid/d1- Developer
- Liquid AI
- Input
- Text
- Output
- Text
- Endpoint
POST https://api.aimlapi.com/v1/decisions
d1 is a decision model from Liquid AI: instead of writing an answer, it evaluates a situation and returns calibrated probabilities across a fixed set of outcomes, in a single call, with zero generated tokens.
What Is Liquid AI d1?
Liquid AI describes decision models as a new class of model purpose-built for structured decisions. A conversational model produces text one token at a time; d1 reads the input in a single forward pass and emits typed values that conform to the question you asked, so your application can branch on them directly instead of parsing prose.
d1 is Liquid AI's first model of this class. On AI/ML API it is served as liquid/d1 through the POST /v1/decisions endpoint.
Technical Reference
- Model family: d1 (decision models)
- Modalities: Text → Text (typed answers)
- Question types: noul, choice, score
- Choice cardinality: 2 to 255 options
- Score levels: 2 to 10 ordered levels
The Three Primitives
Noul, a yes/no with a probability
Returns the probability that the answer is “yes”, between 0 and 1. A boolean on a sliding scale: “Is this message spam?” may come back at 0.92. A noul at 0.5 is maximum uncertainty, and says nothing about degree.
Choice, pick one from a set
Returns the selected option key plus a probability distribution over every option, so you see the runner-up as well as the winner. Options are named in criteria, from 2 up to 255 of them.
Score, rate against a rubric
Returns a probability-weighted position on an ordered scale of 2 to 10 defined levels. The value may be fractional, 1.85 sits between “Medium” and “High”, and comes with a probability per level and a legend mapping each index to its description.
What d1 Brings to the Table
Calibrated probabilities, not just a label
Every answer carries a probability or confidence, so code can threshold on certainty and escalate when the model is unsure rather than acting on a bare classification.
One call, many questions
A single request can carry up to 128 questions over the same state, each with its own type, and every key comes back in answers with a typed result.
No output bill
Output is free, and structurally so: with nothing decoded there are no output tokens to count.
Limits Worth Knowing
d1 reads text only. The content to evaluate is passed as state, a string, a JSON object, or an array of texts, and a request carrying a non-empty images list is refused. The model also does not reason step by step or explain itself: it returns the decision and its probabilities, not a rationale.
Use cases
Liquid AI documents d1 for structured decisions: classification and categorization, routing of tickets, emails and requests, scoring and triage, and content moderation. It is also documented for guardrails and safety checks, as a replacement for LLM-as-judge scoring, for approving an agent's tool calls, and for model routing and cascades.
The three primitives map onto those jobs directly. A Choice question buckets input into named categories and returns a probability for each. A Score question rates input against an ordered rubric and returns an expected level your code can compare against a threshold. A Noul question is a yes/no gate where the probability itself is the useful part, a spam check, a personal-data check, an escalation check.
Liquid AI points to language models instead for free-form text generation, creative writing, multi-turn conversation, complex multi-step reasoning, open-ended Q&A, summarization and code generation.
d1 API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.02 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
How to use the d1 API
View docs
Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/decisions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "liquid/d1",
"questions": null
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "liquid/d1",
"questions": null
}
response = requests.post("https://api.aimlapi.com/v1/decisions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/decisions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "liquid/d1",
"questions": null
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to d1
d1 FAQ
How much does d1 cost?
d1 costs $0.02 per 1M input tokens on AI/ML API, billed as you go with no subscription.
What is a decision model?
Liquid AI describes a decision model as a class of model purpose-built for structured decisions. Instead of generating text token by token, it evaluates a situation and returns calibrated probabilities across a fixed set of outcomes in a single call with zero generated tokens.
What kinds of questions can d1 answer?
Three types, called primitives. Noul is a yes/no question that returns the probability of “yes” between 0 and 1. Choice is a pick-one-from-many question that returns a probability distribution over named options, from 2 up to 255 of them. Score rates the input against an ordered rubric of 2 to 10 defined levels and returns an expected level, which may be fractional, plus a probability for each level.
How many questions can one d1 call include?
Up to 128. The request takes a questions map of question key to typed question, and every key comes back in answers with its own typed result, so one call can classify, score and gate the same input at once.
Does d1 accept images or audio?
No. Decision models read text only: the content to evaluate is passed as state, which may be a string, a JSON object or an array of texts. A request carrying a non-empty images list is refused.
What is d1's context window?
32,768 tokens, covering the state you pass plus the questions and their criteria.
When should I use a language model instead of d1?
Liquid AI points to free-form text generation, creative writing, multi-turn conversation, complex multi-step reasoning, open-ended Q&A, summarization and code generation. d1 is the right tool when the answer is a structured decision, classification, routing, scoring, triage, moderation, guardrails, LLM-as-judge checks, agent tool-call approval, or model routing and cascades.
What is the d1 model ID?
Use liquid/d1 as the model parameter. Requests go to https://api.aimlapi.com/v1/decisions with your AI/ML API key.