LiquidAI: LFM2.5-1.2B-Instruct (free)
LIQUID Developer Architecture Profile
Intelligence (ELO)1053Chatbot Arena Verified
Max Context32,768Tokens
API Cost / 1MFREEBlended Prompt + Completion
Model Capabilities
- Classification
LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support.
Granular Pricing Matrix
Input Tokens (Prompt)Free / 1M
Output Tokens (Completion)Free / 1M
Pricing data via OpenRouter. Sync: 4/30/2026
Evaluate Competitors
VS Engine MatchupLiquidAI: LFM2.5-1.2B-Instruct (free) vs Reka EdgeVS Engine MatchupLiquidAI: LFM2.5-1.2B-Instruct (free) vs Qwen: Qwen3 14BVS Engine MatchupLiquidAI: LFM2.5-1.2B-Instruct (free) vs Qwen: Qwen3 32BVS Engine MatchupLiquidAI: LFM2.5-1.2B-Instruct (free) vs NVIDIA: Nemotron Nano 9B V2VS Engine MatchupLiquidAI: LFM2.5-1.2B-Instruct (free) vs Qwen: Qwen3 235B A22B Instruct 2507VS Engine MatchupLiquidAI: LFM2.5-1.2B-Instruct (free) vs Google: Gemma 3n 4B