# Qwen3-8B

> Small Qwen3 dense model — fast, efficient, good for lightweight chat and tool use.

**ID**: `qwen/qwen3-8b`  
**Creator**: Qwen  
**Category**: text  
**Context**: 128K tokens  
**Input**: $0.12/M  
**Output**: $0.46/M  
**Released**: 2026-07-08  
**Web page**: https://anyrouter.dev/model/qwen/qwen3-8b

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

**Capabilities**: chat, streaming, function-calling, reasoning

**Aliases**: `Qwen/Qwen3-8B`

## 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": "qwen/qwen3-8b",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| siliconflow-byok | $0 | $0 |
| qwencloud | $0 | $0 |
| qwencloud-byok | $0 | $0 |
| mulerouter-byok | $0 | $0 |

## Benchmarks

- **GPQA Diamond**: 0.6
- **HLE**: 0.0
- **τ²-Bench Telecom**: 0.3
- **SciCode**: 0.2

## Source

- Upstream docs: https://docs.siliconflow.com