# LongCat-2.5-Preview

> LongCat-2.5-Preview is Meituan's sparse mixture-of-experts frontier model — ~1.6T total parameters with ~48B active — over a 1M-token context window. It adds native multimodal understanding (image input), stronger coding ability, and a `thinking` toggle, and is built for long-horizon agentic work across terminals, browsers, GUIs, spreadsheets, and design tools. Served over the OpenAI-compatible and Anthropic-compatible APIs.

**ID**: `meituan/longcat-2.5-preview`  
**Creator**: meituan  
**Category**: text  
**Context**: 1M tokens  
**Input**: $0.75/M  
**Output**: $2.95/M  
**Released**: 2026-09-25  
**Web page**: https://anyrouter.dev/model/meituan/longcat-2.5-preview

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

**Capabilities**: chat, streaming, reasoning, coding, agentic, function-calling, vision

**Aliases**: `longcat/longcat-2.5-preview`

## 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": "meituan/longcat-2.5-preview",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| longcat-byok | $0 | $0 |

## Source

- Upstream docs: https://x.com/meituan_longcat/status/2103488918788411728