LiquidAI: LFM2.5-2.6B (free)
LiquidAI LFM2.5-2.6B is designed to process text inputs within a context length of 65,536 tokens and generate up to 8,192 completion tokens. It supports both reasoning and the integration of tools, making it versatile for tasks that require logical thinking or external data access. At this price point, LiquidAI LFM2.5-2.6B is free to use, which makes it an attractive option for users looking to avoid costs. However, as there are no independent benchmark scores available yet, its performance relative to other models remains unproven.
- Model ID
- liquid/lfm-2.5-2.6b:free
- Vendor
- liquid
- Released
- August 2026
- Tokenizer
- Other
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 8,192 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- text only
- Audio
- no
- Moderated
- no
Price & spec history
Tracked daily by PicksByModel since 2026-08-12.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-08-21 | Free | Free | 65,536 |
| 2026-08-12 | Free | Free | 128,000 |
Quick answers
- Is LiquidAI: LFM2.5-2.6B (free) free to use?
- Yes. It is currently listed at no cost per token via OpenRouter, subject to provider rate limits.
- What is LiquidAI: LFM2.5-2.6B (free)'s context window?
- 65,536 tokens, roughly 98 pages of text in a single request.
- Does LiquidAI: LFM2.5-2.6B (free) support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can LiquidAI: LFM2.5-2.6B (free) process images?
- No, it is text-only on the input side.