Primary use stated or inferred cautiously from official documentation.
L
LIQUID AI / d1-ultra
d1-ultra
Liquid AI multimodal decision model released on October 15, 2026. It accepts text and images and returns probabilities for predefined choices, binary questions or scales. It uses the d1-ultra identifier in the decisions API; it does not generate free-form text.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | d1-ultra |
|---|---|
| Model type | Decisions · Multimodal |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 15 OCT 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image |
| Exit | Probabilities |
| Context window | Not published |
| maximum output | Probabilities; no generated tokens |
| Reasoning | Not applicable |
| Published tools | |
| Structured Outings | noul / choice / score |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | Liquid API |
Classification, routing and visual evaluation with structured responses. Requests contain a state, optional images and noul, choice or score questions. It differs from a chatbot and does not replace explanations or open-ended reasoning.
Probabilities need calibration and validation on representative data; do not turn a score into a consequential decision without review. We have not verified model size, maximum context or account limits. Other d1 models’ audio support is not attributed to Ultra.
03 / CAPABILITIES
What it can do
Orientation
Classification, routing and visual evaluation with structured responses. Requests contain a state, optional images and noul, choice or score questions. It differs from a chatbot and does not replace explanations or open-ended reasoning.
Context
Not published · Probabilities; no generated tokens
Tools and integration
Not published
Access
Liquid API
Input modalities
TextImage
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | USD 0.042 / 1M tokens | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | No output tokens | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Official rate: USD 0.042 per million input tokens, with no output tokens. Each question bills the text and all images again. A 1,024 × 1,024 image uses 1,536 tokens under the published formula. Vercel and OpenRouter are announced as upcoming, not verified as available.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
Liquid publishes comparisons with d1 and Jev 1.14 and Decision Index charts, but we do not add figures without a verifiable table and protocol. No in-house tests were run. Evaluation must measure classification, calibration, per-class errors and actual cost per decision.
i No verified scores; Inferama evaluation pending.
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
d1-ultra
Version added to Inferama's verified catalog.
07 / SOURCES