# Qwen3.5-9B

> Qwen3.5-9B is an open-weight model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It has a thinking mode, tool calling and 201 languages.

**ID**: `qwen/qwen3.5-9b`  
**Creator**: Qwen  
**Category**: multimodal  
**Context**: 262K tokens  
**Pricing**: $0.08 / $0.13 per 1M · billed by your provider (BYOK)  
**Released**: 2026-07-08  
**Links**: [Weights on Hugging Face](https://huggingface.co/Qwen/Qwen3.5-9B) · [Announcement](https://qwen.ai/blog?id=qwen3.5) · [AnyRouter release](https://anyrouter.dev/blog/releases/2026-07-31)  
**Web page**: https://anyrouter.dev/model/qwen/qwen3.5-9b

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

**Tokenizer**: Qwen

**Capabilities**: chat, streaming, function-calling, 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": "qwen/qwen3.5-9b",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| deepinfra-byok | $0.10/M (list) | $0.15/M (list) |
| siliconflow-byok | $0.10/M (list) | $0.15/M (list) |
| qwencloud-byok | $0.10/M (list) | $0.15/M (list) |
| openrouter-byok | $0.10/M (list) | $0.14/M (list) |
| mulerouter-byok | $0.10/M (list) | $0.15/M (list) |
| ovhcloud-byok | $0.12/M (list) | $0.18/M (list) |
| nousresearch-byok | $0.08/M (list) | $0.13/M (list) |
| infron-byok | $0.04/M (list) | $0.15/M (list) |
| llmgateway-byok | $0.10/M (list) | $0.15/M (list) |
| huggingface-byok | $0.10/M (list) | $0.15/M (list) |
| requesty-byok | $0.09/M (list) | $0.13/M (list) |
| nano-gpt-byok | $0.10/M (list) | $0.15/M (list) |
| fluence-byok | $0.09/M (list) | $0.14/M (list) |
| cortecs-byok | $0.10/M (list) | $0.15/M (list) |

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

## Benchmarks

- **GPQA Diamond**: 0.8
- **SciCode**: 0.3
- **OTIS Mock AIME**: 0.4

Benchmark data from [Epoch AI](https://epoch.ai/benchmarks) (CC-BY 4.0).

## Model card

- License: Apache-2.0, open weights (https://huggingface.co/Qwen/Qwen3.5-9B) [1]

### Links

- announcement: https://qwen.ai/blog?id=qwen3.5
- model card: https://huggingface.co/Qwen/Qwen3.5-9B

### Sources

1. [Qwen3.5-9B model card](https://huggingface.co/Qwen/Qwen3.5-9B) (accessed 2026-11-11)
2. [Qwen3.5-9B announcement](https://qwen.ai/blog?id=qwen3.5) (accessed 2026-11-11)

## Source

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