# LFM3-VL 2B

> LFM3-VL 2B is Liquid AI's 1.92B-parameter vision-language model for on-device visual understanding. It takes text, images and video as input and reasons step by step before it answers. It has a 128K-token context window and open weights.

**ID**: `liquid/lfm3-vl-2b`  
**Creator**: liquid  
**Category**: multimodal  
**Context**: 128K tokens  
**Pricing**: $0.10 / $0.50 per 1M · billed by your provider (BYOK)  
**Released**: 2026-10-27  
**Links**: [Weights on Hugging Face](https://huggingface.co/LiquidAI/LFM3-VL-2B) · [Announcement](https://www.liquid.ai/blog/lfm3) · [AnyRouter release](https://anyrouter.dev/blog/releases/2026-11-15-lfm3-vl-2b)  
**Web page**: https://anyrouter.dev/model/liquid/lfm3-vl-2b

**Input modalities**: text, image  
**Output modalities**: text  

**Tokenizer**: Other

**Capabilities**: chat, streaming, reasoning, vision

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "liquid/lfm3-vl-2b",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| infron-byok | $0.10/M (list) | $0.50/M (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Model card

- Total parameters: 1.92B [2]
- Native context: 131072 tokens [2]
- License: LFM Open License v1.0, open weights (https://huggingface.co/LiquidAI/LFM3-VL-2B) [2]

### Strengths [2]

- The first LFM vision model that takes video as input, sampled at 2 fps.
- Reasons step by step before answering, which helps with math, charts and multi-step visual questions.
- Finds objects and reasons about their placement, a base for robotics work.

### Known limits [2]

- Not recommended for coding, multi-turn conversations or complex reasoning.

### Use cases [2]

- Questions about video, documents, charts and app screens.
- Object finding and spatial reasoning for robots.

### Links

- announcement: https://www.liquid.ai/blog/lfm3
- model card: https://huggingface.co/LiquidAI/LFM3-VL-2B
- docs: https://docs.liquid.ai/lfm/getting-started/welcome

### Sources

1. [Introducing LFM3: Every Modality for Specialized Intelligence](https://www.liquid.ai/blog/lfm3) (accessed 2026-11-15)
2. [LiquidAI/LFM3-VL-2B model card](https://huggingface.co/LiquidAI/LFM3-VL-2B) (accessed 2026-11-15)

## Source

- Upstream docs: https://www.liquid.ai/blog/lfm3