DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching …
Model details →DeepSeek: DeepSeek V3.1 vs LiquidAI: LFM2.5-1.2B-Thinking (free)
LiquidAI: LFM2.5-1.2B-Thinking (free) wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
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 designed to provide high…
Model details →Side-by-side comparison
| Capability | DeepSeek: DeepSeek V3.1 | LiquidAI: LFM2.5-1.2B-Thinking (free) | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 33K | 33K | Tie |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.15 | $0.00 | 🏆 LiquidAI: LFM2.5-1.2B-Thinking (free) |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.75 | $0.00 | 🏆 LiquidAI: LFM2.5-1.2B-Thinking (free) |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | — | 🏆 DeepSeek: DeepSeek V3.1 |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is DeepSeek: DeepSeek V3.1 better than LiquidAI: LFM2.5-1.2B-Thinking (free)?
LiquidAI: LFM2.5-1.2B-Thinking (free) wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between DeepSeek: DeepSeek V3.1 and LiquidAI: LFM2.5-1.2B-Thinking (free)?
Input: $0.15 vs $0.00 per 1M tokens. Output: $0.75 vs $0.00 per 1M tokens.
What context windows do DeepSeek: DeepSeek V3.1 and LiquidAI: LFM2.5-1.2B-Thinking (free) support?
DeepSeek: DeepSeek V3.1 supports up to 33K tokens. LiquidAI: LFM2.5-1.2B-Thinking (free) supports up to 33K tokens.
Do both DeepSeek: DeepSeek V3.1 and LiquidAI: LFM2.5-1.2B-Thinking (free) support tool calling?
DeepSeek: DeepSeek V3.1: yes. LiquidAI: LFM2.5-1.2B-Thinking (free): not advertised.