When was D1 Ultra released?

Liquid AI released D1 Ultra on 15 Oct 2026. It is available through the Opper gateway.

Does D1 Ultra support zero data retention?

Yes. D1 Ultra is available with zero data retention on Liquid AI through the Opper gateway.

Where is D1 Ultra hosted?

D1 Ultra runs on US hosting routes through the Opper gateway.

Is D1 Ultra trained on prompts and outputs?

No. Every hosting route for D1 Ultra is configured so customer prompts and outputs are not used to train models by default.

D1 Ultra

by Liquid AI

Announcement · All Liquid AI releases

d1-ultra is the largest model in Liquid AI's d1 decision family, built on a larger open-weight base model with Liquid's own customizations and trained to produce well-calibrated probabilities. You send a state (text or any JSON value) and named questions, and it returns typed answers: the probability that a statement is true, a choice among options you define, or a position on your own rubric, each with a full probability distribution. It generates no text, so answers cannot fall outside the options given. It speaks the same request and response format as TypeSafe's System One API, so code written for Jev can switch models by changing the model name. Liquid reports it ahead of d1 and Jev 1.14 across its own evaluations, with the largest gains on knowledge-heavy questions. Use it for harder, messier decisions where accuracy matters most, such as checking a claim against a specification or grading free-form answers. d1.1 is the cheaper and faster choice for high-volume routing. d1-ultra is available through Liquid AI's API; its weights are not published.

Call D1 Ultra on Opper through the System One evaluation API. Sign up without a credit card. Get started

Get your API key Evaluate via API Compare

Key info

Input

Output

Features

Context window

33K

Max output

—

Input price

$0.04 /1M

Output price

$0 /1M

Released

15 Oct 2026

US residency available
Zero data retention on pay-as-you-go
No training by default

Available routes

D1 Ultra runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
Liquid AI	US		No	$0.04	$0	Input price

Live routes and prices as JSON: api.opper.ai/v3/models?q=liquid%2Fd1-ultra

Data handling per route

Each route hosting D1 Ultra has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Liquid AI — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: Keeps nothing
Caching: Not cached
Transfer mechanism: SCCs

Best for

The model directory pages that list D1 Ultra.

Listed inDecision models

Get started

Call D1 Ultra through the Opper gateway with one API key. Evaluate state against typed questions using TypeSafe’s System One API for yes/no decisions, classification, and rubric scoring.

See the Opper evaluation guide and the TypeSafe API reference for question types and response formats. Compare every decision model, on one API.

D1 Ultra is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1curl https://api.opper.ai/v3/compat/v1/systemone \
2  -H "Authorization: Bearer $OPPER_API_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "liquid/d1-ultra",
6    "state": "The customer cannot sign in and needs help immediately.",
7    "questions": {
8      "is_urgent": {
9        "type": "noul",
10        "instructions": "Does the customer need urgent help?"
11      }
12    }
13  }'