LLM Comparison
LFM2.5-1.2B-Thinking vs MiniMind
Side-by-side specs, pricing & capabilities · Updated September 2026
Add to comparison
2/6 modelsSame tier:
| Organization | ||
| OpenTools Score | ||
| Family | LFM2.5-1.2B-Thinking | MiniMind |
| Status | Current | Current |
| Release Date | Jan 2026 | Sep 2026 |
| Context Window | 33K tokens | 1K tokens |
| Input Price | — | — |
| Output Price | — | — |
| Pricing Notes | Free tier available on OpenRouter with rate limits | Open-source project; API pricing is not applicable unless a downstream host adds serving costs. |
| Capabilities | textcodeextended-thinking | texteducationtraining |
| Training Cutoff | — | Not specified |
| Max Output | — | 1K tokens |
| API Identifier | liquid/lfm-2.5-1.2b-thinking:free | jingyaogong/minimind |
| Benchmarks | ||
| GPQA Diamond | 33.9394artificial-analysis | — |
| View LFM2.5-1.2B-Thinking | View MiniMind | |
Liquid AI
LFM2.5-1.2B-Thinking
LFM2.5-1.2B-Thinking is a large language model from Liquid AI. Supports up to 32,768 token context window. Available free with rate limits on OpenRouter.
Jingyao Gong
MiniMind
MiniMind is a small open-source language-model training project that demonstrates how to train a 64M-parameter LLM from scratch. The repository is aimed at builders who want a compact, inspectable model-training path rather than a hosted frontier API.
More Comparisons
Looking for more AI models?
Browse All LLMs