> For the complete documentation index, see [llms.txt](https://docs.ionos.com/cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ionos.com/cloud/ai/ai-model-hub/models/llms/qwen3-5-9b.md).
# Qwen3.5 9B
**Summary:** Qwen3.5-9B is a compact multimodal model from Alibaba Cloud's Qwen team, built on a hybrid architecture that combines linear attention with standard attention layers and an integrated vision encoder. Despite its compact 9B parameter size, the model natively supports an extended 262k token context window, reasoning ("thinking mode"), tool calling, and multilingual understanding across 201 languages and dialects. In addition to text, it processes both image and video input, making it a fast, cost-efficient choice for conversational agents, real-time assistants, and vision-language applications.
| **Intelligence** | **Speed** | **Input** | **Output** |
| :-----------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------------------------: |
|   |    |    |    |
| *Medium* | *High* | *Text, Image, Video* | *Text* |
## Central parameters
**Description:** Compact multimodal model from Alibaba Cloud with 9B parameters, combining hybrid linear attention with standard attention layers and a vision encoder for fast, efficient inference.
**Model identifier:** `Qwen/Qwen3.5-9B`
## IONOS CLOUD AI Model Hub Lifecycle and Alternatives
| **IONOS CLOUD start date** | **End of Life** | **Alternative** | **Successor** |
| :------------------------: | :-------------: | :-------------: | :-----------: |
| *July 22, 2026* | N/A | | |
## Origin
| **Provider** | **Country** | **License** | **Flavor** | **Release** |
| :---------------------------------------------------------------------------------: | :---------: | :-------------------------------------------------------------------------------------------------: | :--------: | :-------------: |
| [**Alibaba Cloud**](https://www.alibabacloud.com/) | China | [**Apache 2.0**](https://www.apache.org/licenses/LICENSE-2.0.html) | Instruct | *February 2026* |
## Technology
| **Context window** | **Parameters** | **Quantization** | **Multilingual** | **Further details** |
| :----------------: | :------------: | :--------------: | :--------------: | :-----------------------------------------------------------------------------------------: |
| *262k* | *9B* | *FP8* | *Yes* | [**Hugging Face**](https://huggingface.co/Qwen/Qwen3.5-9B) |
## Modalities
| **Text** | **Image** | **Video** | **Audio** |
| :--------------: | :-------: | :-------: | :-----------: |
| Input and output | Input | Input | Not supported |
{% hint style="info" %}
\*\*Note:\*\*The video content is provided as a URL using the `video_url` content type. The AI Model Hub fetches the video from the URL, so the URL must be public. You can include up to four images in a single request.
{% endhint %}
## Endpoints
| **Chat completions** | **Embeddings** | **Image generation** |
| :------------------: | :------------: | :------------------: |
| v1/chat/completions | Not supported | Not supported |
## Features
| **Streaming** | **Reasoning** | **Tool calling** |
| :-----------: | :-----------: | :--------------: |
| Supported | Supported | Supported |
### Reasoning example
Qwen3.5-9B operates in thinking mode by default, generating an internal reasoning trace before producing its final response. It makes the model well-suited for complex, multi-step reasoning tasks.
Unlike models that offer configurable reasoning effort levels (`low`, `medium`, `high`), Qwen3.5-9B does not support this granularity. Instead, reasoning is either `on` (default) or `off`. To deactivate it, set `"reasoning_effort": "none"`.
{% hint style="warning" %}
**Note:** The reasoning trace counts toward `max_tokens`. If `max_tokens` is set too low, reasoning can consume the entire token budget, leaving no tokens for the final answer. Activating reasoning also increases response latency, since the model generates the reasoning trace in addition to the final answer.
{% endhint %}
#### Request
```json
{
"stream": false,
"model": "Qwen/Qwen3.5-9B",
"messages": [
{
"role": "user",
"content": "Answer me with one letter. Maybe A."
}
]
}
```
#### Response (shortened for readability)
```json
{
"choices": [
{
"message": {
"role": "assistant",
"content": "A",
"reasoning": "User asks to answer with one letter, maybe A. So respond with a single letter."
}
}
]
}
```
#### Deactivate reasoning
To skip the internal reasoning trace and return only the final answer, set `"reasoning_effort": "none"`.
```json
{
"stream": false,
"model": "Qwen/Qwen3.5-9B",
"reasoning_effort": "none",
"messages": [
{
"role": "user",
"content": "Answer me with one letter. Maybe A."
}
]
}
```
## Usage example
### Chat completions
The following example demonstrates how to use **Qwen3.5-9B** for everyday conversational tasks, such as drafting a concise product description.
**API Endpoint:** `POST https://openai.inference.de-txl.ionos.com/v1/chat/completions`
**Request:**
```json
{
"model": "Qwen/Qwen3.5-9B",
"messages": [
{
"role": "system",
"content": "You are a helpful marketing assistant. Write clear, concise product copy."
},
{
"role": "user",
"content": "Write a one-sentence product description for a stainless steel water bottle that keeps drinks cold for 24 hours."
}
],
"temperature": 0.5,
"max_tokens": 1000
}
```
**Response:**
```json
{
"id": "chatcmpl-890",
"object": "chat.completion",
"created": 1677652289,
"model": "Qwen/Qwen3.5-9B",
"choices": [{
"index": 0,
"message": {
"role": "assistant",
"content": "Stay refreshed all day with our double-walled stainless steel water bottle, engineered to keep your drinks ice-cold for a full 24 hours.",
"reasoning": "The user wants a single-sentence product description for an insulated stainless steel water bottle highlighting 24-hour cold retention. I will keep it to one sentence and emphasize the key benefit."
},
"finish_reason": "stop"
}],
"usage": {
"prompt_tokens": 41,
"completion_tokens": 33,
"total_tokens": 74
}
}
```
### Vision model example
```json
{
"model": "Qwen/Qwen3.5-9B",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What do you see in this image?"
},
{
"type": "image_url",
"image_url": {
"url": "https://www.ionos.com/favicon.ico?v2",
"detail": "auto"
}
}
]
}
],
"temperature": 0.7,
"max_tokens": 1000
}
```
### Video input example
Qwen3.5-9B also accepts video input. Pass the clip with the `video_url` content type; the AI Model Hub fetches the file, so the URL must be public.
```json
{
"model": "Qwen/Qwen3.5-9B",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Describe what happens in this video."
},
{
"type": "video_url",
"video_url": {
"url": "https://example.com/sample-clip.mp4"
}
}
]
}
],
"temperature": 0.7,
"max_tokens": 1000
}
```
### Stream chat completions
To receive responses in real time, you can use streaming. When streaming is selected, usage statistics are not included by default. To obtain usage information in the final stream chunk, you must explicitly set `"stream_options": {"include_usage": true}`.
**API Endpoint:** `POST https://openai.inference.de-txl.ionos.com/v1/chat/completions`
**Request:**
```json
{
"model": "Qwen/Qwen3.5-9B",
"messages": [
{
"role": "user",
"content": "Compose a poem about the sea."
}
],
"stream": true,
"stream_options": {
"include_usage": true
}
}
```
**Response:**
```json
...
data: {"choices":[],"created":1769419547,"id":"chatcmpl-3d0323bb-67f8-41c5-b757-8fc5a48230f4","model":"Qwen/Qwen3.5-9B","object":"chat.completion.chunk","usage":{"completion_tokens":26,"prompt_tokens":78,"total_tokens":104}}
data: [DONE]
```
## Rate limits
Rate limits ensure fair usage and reliable access to the AI Model Hub. In addition to the [contract-wide rate limits](/cloud/ai/ai-model-hub/how-tos/rate-limits.md), no model-specific limits apply.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.ionos.com/cloud/ai/ai-model-hub/models/llms/qwen3-5-9b.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.