Liquid
Release: 2026-10-17
Tested on: 2026-10-17 11:00
liquid/d1-ultra::none
-OtherClosed Summary
d1-ultra scores 2.7 on AI BENCHY and ranks #421. It has 10.0 reliability, a 20.3% pass rate, $0.003 total cost, and 531ms average response time.
Model facts
Researched on 2026-10-17
- Parameters
- -
- Architecture
- Other
- Availability
- Closed
- License
- -
Liquid identifies d1-ultra as a hosted multimodal decision model built on a larger open-weight backbone, without disclosing the exact checkpoint size or architecture or publishing its weights. Treat this hosted checkpoint as closed; do not transfer another d1 model's size or license. It returns typed probabilities for text or optional images with no generated tokens or exposed reasoning controls. The exact OpenRouter decision endpoint publishes training=false and retainsPrompts=false, overriding Liquid's training-enabled provider-wide default. Fallback date records this onboarding request date.
2.7
Consistency
4.9
10.0
$0.003
Total Output Tokens
0
Total Input Tokens
55,956
Input Price
$0.042 / 1M
Output Price
$0.000 / 1M
Cache Read Price
$0.042 / 1M
Cache Write Price
N/A
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Wrong Tests: 8
Attempt pass rate: 20.3%
Benchmark coverage: 36/69 attempts. Choices supplied by adapters. Supports 12/23 tests. Other tests are unsupported, not failed. Score uses the full suite.
Flaky tests
1
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Charts
Choose the first model, then click a second model to open a side-by-side page.
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
d1-ultradefaultvsSpan-02defaultd1-ultradefaultvsJev 1.13defaultd1-ultradefaultvsCommand A+lowd1-ultradefaultvsDecider V1.2defaultd1-ultradefaultvsCommand A+noned1-ultradefaultvsDecider V1.1 27Bdefaultd1-ultradefaultvsCommand A+highd1-ultradefaultvsDrex v1.5defaultd1-ultradefaultvsXing4.0 29b A4bnoneFree Availabled1-ultradefaultvsGPT-6 Luna Decisionsdefault
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 0.0 | 0.0 | |
| Anti-AI Tricks | 4.0 | 7.5 | |
| Coding | 5.3 | 4.3 | |
| Combined | 0.0 | 0.0 | |
| Data parsing and extraction | 6.5 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 0.0 | 0.0 | |
| Instructions following | 1.5 | 5.0 | |
| Puzzle Solving | 1.7 | 3.3 | |
| Tool Calling | 0.0 | 0.0 | |
| Trivia | 0.0 | 0.0 |