LiquidAI: LFM2-8B-A1B
Analysis Summary
LiquidAI: LFM2-8B-A1B sits in the Emerging tier on our leaderboard, ranked #271 of 525 published models on overall intelligence. At $0.010 input and $0.020 output per 1M tokens, it is among the most expensive on the market. It offers a mid-sized context window.
Editorial notes
LiquidAI's LFM2-8B-A1B is an ultra-cheap model with near-zero pricing, but benchmark performance is very limited across all dimensions. It is best considered for edge or on-device use cases where cost is paramount, not for substantive business applications.
Assessed April 23, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
LFM2-8B-A1B is an efficient on-device Mixture-of-Experts (MoE) model from Liquid AI’s LFM2 family, built for fast, high-quality inference on edge hardware. It uses 8.3B total parameters with only ~1.5B active per token, delivering strong performance while keeping compute and memory usage low—making it ideal for phones, tablets, and laptops.
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does LiquidAI: LFM2-8B-A1B stack up?
Compare side-by-side with other emerging models.
Model Information
| OpenRouter ID |
liquid/lfm2-8b-a1b
|
| Provider | liquid |
| Release Date | October 20, 2025 |
| Context Length | 32,768 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.01 | $0.000010 |
| Output | $0.02 | $0.000020 |
