# LingDT-3.0-flash

> LingDT-3.0-flash is a 124B-parameter Mixture-of-Experts model from Ant Digital Technologies, with about 5.1B parameters activated per token. It is designed with token efficiency and production-scale agentic inference as key priorities, so developers can finish more useful work within tight token, latency, and serving-cost budgets.

**ID**: `antdigital/lingdt-3.0-flash`  
**Creator**: antdigital  
**Category**: text  
**Context**: 256K tokens  
**Pricing**: $0.02 / $0.06 per 1M · billed by your provider (BYOK)  
**Released**: 2026-08-20  
**Web page**: https://anyrouter.dev/model/antdigital/lingdt-3.0-flash

**Input modalities**: text  
**Output modalities**: text  

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

## 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": "antdigital/lingdt-3.0-flash",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| computrix-byok | $0.02/M (list) | $0.06/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

- Architecture: mixture of experts [1]
- Total parameters: 124B [1]
- Active parameters: 5.1B [1]
- Native context: 256000 tokens [1]

### Strengths [1]

- Token-efficient design for production-scale agentic inference

### Sources

1. [LingDT-3.0-flash on Computrix](https://computrix.ai/sg/models/modelservice-1787215586789001213) (accessed 2026-10-27)