LiquidAI d1-omni-600M

Liquid AIDecision modelOpen weights

LiquidAI d1-omni-600M by Liquid AI is a decision model: it answers typed questions with a probability for each allowed answer instead of generating text. It scores 9.1 on the Jev Decision Index (rank 142).

Pricing

No hosted price is listed. The weights are open: the cost is your own compute.

Specifications

Provider: Liquid AI
Parameters: 587M
Released: Oct 2026
Open weights: Yes
Question types: Choice (one of N options), Score (ordered rubric), Yes / no
Mechanism: Encoder classifier
Backbone: LiquidAI/LFM2.5-Encoder-350M
Jev-compatible request: Yes
Runs on CPU: Yes
License: lfm1.0
Hugging Face: LiquidAI/d1-omni-600M

Benchmarks

Jev Decision IndexECE 0.128: 9.1
Benchmark Heaven JevBench (Capability): 32.8

Jev Decision Index: public 17.9, ECE 0.128, Brier 0.586. Lower ECE means its probabilities can be taken at face value.

Self-reported by the publisher

The model's own claims, often on its own sets or a self-run copy of a public suite. Not independently verified and never ranked alongside measured results.

Jev Decision Index public suite (self-run)Self-reportedDecision Index public balanced skill, edition 0.3 kit (release-v3), self-run: 14.6

Speed & latency

Median latency per call (Decision Index)

11 ms

Compare LiquidAI d1-omni-600M with…

LiquidAI d1-omni-600M vs amos-1-large—/1M in LiquidAI d1-omni-600M vs amos-1-medium—/1M in LiquidAI d1-omni-600M vs Celeris-1 Decision$0.04/1M in LiquidAI d1-omni-600M vs ScaleDown Classify-1$0.04/1M in LiquidAI d1-omni-600M vs Cloudflare clef—/1M in LiquidAI d1-omni-600M vs Cloudflare clef-flash—/1M in

FAQ

How much does LiquidAI d1-omni-600M cost?

LiquidAI d1-omni-600M has no hosted price listed; its weights are open, so the cost is the compute you run it on.

What questions can LiquidAI d1-omni-600M answer?

LiquidAI d1-omni-600M answers choice (one of n options), score (ordered rubric), yes / no questions, returning a probability for each allowed answer.

Is LiquidAI d1-omni-600M well calibrated?

On the Jev Decision Index its expected calibration error (ECE) is 0.128; below about 0.05, a stated 80% confidence is right roughly 80% of the time.

Is LiquidAI d1-omni-600M open weight, and can it run on a CPU?

Yes, LiquidAI d1-omni-600M has open weights. It is small enough to run on a CPU.

Data as of 2026-10-14. Source: Metatext decision-model catalogue, 2026-10-14 (Jev Decision Index, Benchmark Heaven JevBench, Hugging Face). Pricing is per 1M tokens (USD); confirm with the provider before production use.