← Back to Directory

LiquidAI: LFM2.5-1.2B-Thinking (free)

LIQUID Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1058Chatbot Arena Verified
Max Context32,768Tokens
API Cost / 1MFREEBlended Prompt + Completion

Model Capabilities

    LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...

    Granular Pricing Matrix

    Input Tokens (Prompt)Free / 1M
    Output Tokens (Completion)Free / 1M

    Pricing data via OpenRouter. Sync: 6/14/2026

    Evaluate Competitors

    VS Engine MatchupLiquidAI: LFM2.5-1.2B-Thinking (free) vs Pareto Code RouterVS Engine MatchupLiquidAI: LFM2.5-1.2B-Thinking (free) vs IBM: Granite 4.0 MicroVS Engine MatchupLiquidAI: LFM2.5-1.2B-Thinking (free) vs NVIDIA: Nemotron Nano 9B V2 (free)VS Engine MatchupLiquidAI: LFM2.5-1.2B-Thinking (free) vs Qwen: Qwen3 Coder 480B A35B (free)VS Engine MatchupLiquidAI: LFM2.5-1.2B-Thinking (free) vs Meta: Llama 4 ScoutVS Engine MatchupLiquidAI: LFM2.5-1.2B-Thinking (free) vs Owl Alpha