# LFM2.5-24B-A2B: price, benchmarks, context

- **URL canônica:** https://meirinho.com.br/en/ia/modelos/lfm-2-5-24b-a2b/
- **Idioma:** en
- **Atualizado:** 2026-11-17

---
**insufficient data** — 0 of 4 benchmarks

Methodology v2 · updated November 21, 2026 · [Technical tie](https://meirinho.com.br/en/ia/modelos/metodologia/#empate-tecnico) · [Minimum of 4 benchmarks](https://meirinho.com.br/en/ia/modelos/metodologia/#minimo-3-benchmarks) · [Methodology](https://meirinho.com.br/en/ia/modelos/metodologia/)

Liquid AI

# LFM2.5-24B-A2B

Benchmarks, price, context and versions

Input US$/1M

Official pricing

Output US$/1M

Official pricing

Context

tokens

## Direct answer

**Direct answer:** LFM2.5-24B-A2B is a model from Liquid AI. US$ 0.05 per 1 million input tokens and US$ 0.70 per 1 million output tokens.

## ✓ Good for

- high-volume use (input price in the cheapest 25%)
- running on your own infrastructure (open weights)

## ✕ Not the best for

- Not enough data in the open sources this section uses to build this block.

This block follows a rule of this section, using source data: if the model is in the top 25% of the metric, the item goes under "Good for"; if it is in the bottom half, it goes under "Not the best for". The middle band appears in neither. The price is official pricing, published by the lab itself for its own API. Context uses OpenRouter. Scores use Epoch AI or OpenRouter Benchmarks, in the latest version we checked.

## Benchmarks

| no data |
| --- |

## Input US$/1M · Output US$/1M

Input US$/1M

US$ 0.05

Third-party provider pricing, OpenRouter: US$ 0.05 / US$ 0.70

Output US$/1M

US$ 0.70

Cache read US$/1M

US$ 0.025

## Key specs

| Lab | [Liquid AI](https://meirinho.com.br/en/ia/modelos/lab/liquid-ai/) |
| --- | --- |
| Origin | the US |
| Family | LFM provisional data |
| Weights[? what it is](https://meirinho.com.br/en/ia/modelos/glossario/pesos-abertos/) | open |
| License | [lfm1.0](https://huggingface.co/LiquidAI/LFM2.5-24B-A2B) |
| Also known as | API name: [LFM2.5-24B-A2B](https://www.liquid.ai/pricing) |
| Context[?](https://meirinho.com.br/en/ia/modelos/glossario/janela-de-contexto/) | 128,000 tokens |
| Parameters | 23,971,585,280 |
| Input | text |
| OpenRouter usage[?](https://meirinho.com.br/en/ia/modelos/glossario/uso-no-openrouter/) | <0.01% OpenRouter |
| Downloads (30 days)[?](https://meirinho.com.br/en/ia/modelos/glossario/downloads-hugging-face/) | 39,597 |
| Use cases provisional data | [Text](https://meirinho.com.br/en/ia/modelos/uso/texto/) [Agents](https://meirinho.com.br/en/ia/modelos/uso/agentes/) |
| Dates in sources | no official dateOctober 13, 2026, listed on OpenRouterOctober 12, 2026, Hugging Face repo created |

Collected November 17, 2026

## Version history

- November 6, 2026 [LiquidAI: LFM3-1.7B](https://openrouter.ai/liquid/lfm-3-1.7b) OpenRouter, listed on OpenRouter
- October 24, 2026 [LFM3-1.7B-FP8](https://huggingface.co/LiquidAI/LFM3-1.7B-FP8) Hugging Face Hub, Hugging Face repo created
- October 23, 2026 [LFM3-1.7B](https://huggingface.co/LiquidAI/LFM3-1.7B) Hugging Face Hub, Hugging Face repo created
- October 13, 2026 [LiquidAI: LFM2.5-24B-A2B](https://openrouter.ai/liquid/lfm-2.5-24b-a2b) OpenRouter, listed on OpenRouter
- October 12, 2026 [LFM2.5-24B-A2B-FP8](https://huggingface.co/LiquidAI/LFM2.5-24B-A2B-FP8) Hugging Face Hub, Hugging Face repo created
- October 12, 2026 [LFM2.5-24B-A2B](https://huggingface.co/LiquidAI/LFM2.5-24B-A2B) Hugging Face Hub, Hugging Face repo created

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch.

## Sources for this model

- Official pricing, [Liquid AI](https://www.liquid.ai/pricing).
- No official launch announcement.
- Weights and license (lfm1.0), [Hugging Face](https://huggingface.co/LiquidAI/LFM2.5-24B-A2B).

## FAQ

LFM2.5-24B-A2B is a model from Liquid AI, with open weights, used for text, agents.

US$ 0.05 per 1 million input tokens and US$ 0.70 per 1 million output tokens.

128,000 tokens, per OpenRouter.

Yes, it has open weights. License: lfm1.0.

No data: there is no SWE-bench Verified measurement for it in open sources.

It was made by Liquid AI, a lab from the US.

provisional data

## Compare with

### Models from Liquid AI

- [LFM3-1.7B](https://meirinho.com.br/en/ia/modelos/lfm-3-1-7b/)

[See lab](https://meirinho.com.br/en/ia/modelos/lab/liquid-ai/)

## How to cite

If you use this data, cite the page and the date you accessed it.

```
Adriano Meirinho. "LFM2.5-24B-A2B". meirinho.com.br. https://meirinho.com.br/en/ia/modelos/lfm-2-5-24b-a2b/. Accessed November 21, 2026.
```

Third-party data follows the license of each source. The full table is available as [CSV](https://meirinho.com.br/ia/modelos/dados.csv) and [JSON](https://meirinho.com.br/ia/modelos/dados.json).

[#](#)
