LiquidAI: LFM2-8B-A1B
LIQUID Developer Architecture Profile
Intelligence (ELO)1150Chatbot Arena Verified
Max Context32,768Tokens
API Cost / 1M$0.03Blended Prompt + Completion
Model Capabilities
- Drafting
- Classification
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.
Granular Pricing Matrix
Input Tokens (Prompt)$0.01 / 1M
Output Tokens (Completion)$0.02 / 1M
Pricing data via OpenRouter. Sync: 3/16/2026
Evaluate Competitors
VS Engine MatchupLiquidAI: LFM2-8B-A1B vs ByteDance Seed: Seed-2.0-LiteVS Engine MatchupLiquidAI: LFM2-8B-A1B vs Qwen: Qwen3.5-35B-A3BVS Engine MatchupLiquidAI: LFM2-8B-A1B vs Qwen: Qwen3.5-FlashVS Engine MatchupLiquidAI: LFM2-8B-A1B vs MiniMax: MiniMax M2.5 (free)VS Engine MatchupLiquidAI: LFM2-8B-A1B vs MiniMax: MiniMax M2.5VS Engine MatchupLiquidAI: LFM2-8B-A1B vs StepFun: Step 3.5 Flash (free)