Enterprise DNA
Directories / Models / Compare

Model comparison

LFM2.5-1.2B-Instruct (free) vs LFM2.5-1.2B-Thinking (free)

Compare LFM2.5-1.2B-Instruct (free) and LFM2.5-1.2B-Thinking (free): input/output $/Mtoken, context window, modalities, and license. OpenRouter-synced pricing.

Metric LFM2.5-1.2B-Instruct (free) LFM2.5-1.2B-Thinking (free)
Provider Liquid Liquid
Context window 32,768 32,768
Input $/Mtok $0 $0
Output $/Mtok $0 $0
Modalities text text
License open-weights open-weights

Quick take

On input price, LFM2.5-1.2B-Instruct (free) is cheaper at $0/Mtok. For context window, LFM2.5-1.2B-Instruct (free) leads with 32,768 tokens.

Pick based on your workload: high-volume cheap inference vs long-document / agent loops. Enterprise DNA can wire either model into Omni with evals, secrets, and job orchestration.