LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
Model details →LiquidAI: LFM2.5-2.6B (free) vs Perceptron: Perceptron Mk1.5
LiquidAI: LFM2.5-2.6B (free) wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...
Model details →Side-by-side comparison
| Capability | LiquidAI: LFM2.5-2.6B (free) | Perceptron: Perceptron Mk1.5 | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 66K | 37K | 🏆 LiquidAI: LFM2.5-2.6B (free) |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.00 | $0.15 | 🏆 LiquidAI: LFM2.5-2.6B (free) |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.00 | $1.50 | 🏆 LiquidAI: LFM2.5-2.6B (free) |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | — | Yes | 🏆 Perceptron: Perceptron Mk1.5 |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is LiquidAI: LFM2.5-2.6B (free) better than Perceptron: Perceptron Mk1.5?
LiquidAI: LFM2.5-2.6B (free) wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between LiquidAI: LFM2.5-2.6B (free) and Perceptron: Perceptron Mk1.5?
Input: $0.00 vs $0.15 per 1M tokens. Output: $0.00 vs $1.50 per 1M tokens.
What context windows do LiquidAI: LFM2.5-2.6B (free) and Perceptron: Perceptron Mk1.5 support?
LiquidAI: LFM2.5-2.6B (free) supports up to 66K tokens. Perceptron: Perceptron Mk1.5 supports up to 37K tokens.
Do both LiquidAI: LFM2.5-2.6B (free) and Perceptron: Perceptron Mk1.5 support tool calling?
LiquidAI: LFM2.5-2.6B (free): yes. Perceptron: Perceptron Mk1.5: yes.