> ## Documentation Index
> Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Qwen3.6-Plus
> Qwen3.6-Plus multimodal model via AnyFast's OpenAI-compatible API.
Qwen3.6-Plus is Alibaba's flagship Qwen3.6 multimodal model, available through AnyFast's OpenAI-compatible Chat Completions API. Use the model ID `qwen3.6-plus` for text generation, image and video understanding, tool calling, and structured output.
## Key capabilities
* **1M-token context window** — Process long documents, conversations, and multimodal context.
* **64K maximum output** — Generate long-form answers, code, and structured results.
* **Multimodal input** — Accept text, images, and videos in the same conversation.
* **Large media capacity** — Up to 256 images and 64 videos in a request. Videos can be up to 2 hours or 2 GB.
* **Function calling** — Let the model select and call application-defined functions.
* **Built-in tools** — Use supported web search and code execution tools when enabled by the upstream service.
* **Structured output** — Request JSON output in non-thinking mode.
## Quick example
```bash cURL theme={null}
curl --request POST \
--url https://www.anyfast.ai/v1/chat/completions \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "qwen3.6-plus",
"messages": [
{"role": "user", "content": "Explain how a solar eclipse happens."}
],
"temperature": 1,
"max_completion_tokens": 1024
}'
```
```python Python theme={null}
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://www.anyfast.ai/v1",
)
response = client.chat.completions.create(
model="qwen3.6-plus",
messages=[
{"role": "user", "content": "Explain how a solar eclipse happens."}
],
temperature=1,
max_completion_tokens=1024,
)
print(response.choices[0].message.content)
```
## Image and video input
Use OpenAI-compatible content parts for remote media URLs or base64 data URIs. Qwen3.6-Plus accepts up to 256 images and 64 videos in a request.
```python theme={null}
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://www.anyfast.ai/v1")
response = client.chat.completions.create(
model="qwen3.6-plus",
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": "Compare the image and video, then summarize the differences."},
{
"type": "image_url",
"image_url": {"url": "https://example.com/reference.jpg"},
},
{
"type": "video_url",
"video_url": {"url": "https://example.com/sample.mp4"},
},
],
}
],
max_completion_tokens=1024,
)
print(response.choices[0].message.content)
```
## Thinking and structured output
Set `enable_thinking` through `extra_body` when using the OpenAI SDK. For structured output and tool-calling workflows, follow the upstream requirement to use non-thinking mode.
```python theme={null}
response = client.chat.completions.create(
model="qwen3.6-plus",
messages=[{"role": "user", "content": "Return the result as JSON."}],
response_format={"type": "json_object"},
extra_body={"enable_thinking": False},
)
```
## Function calling
Define application functions in the `tools` array. When the model returns `tool_calls`, execute the selected function in your application, append the tool result to `messages`, and send the conversation back to the model.
```python theme={null}
tools = [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the current weather for a city.",
"parameters": {
"type": "object",
"properties": {"city": {"type": "string"}},
"required": ["city"],
},
},
}
]
response = client.chat.completions.create(
model="qwen3.6-plus",
messages=[{"role": "user", "content": "What is the weather in Singapore?"}],
tools=tools,
extra_body={"enable_thinking": False},
)
print(response.choices[0].message.tool_calls)
```
## Streaming
Set `stream` to `true` to receive Server-Sent Events. Set `stream_options.include_usage` to `true` if the final chunk should include token usage.
```python theme={null}
stream = client.chat.completions.create(
model="qwen3.6-plus",
messages=[{"role": "user", "content": "Write a short story about the ocean."}],
stream=True,
stream_options={"include_usage": True},
)
for chunk in stream:
if chunk.choices:
print(chunk.choices[0].delta.content or "", end="")
```
## Parameters
| Parameter | Type | Required | Description |
| ----------------------- | ---------------- | -------: | ------------------------------------------------------------------------------------------------------------- |
| `model` | string | Yes | Must be `qwen3.6-plus`. |
| `messages` | array | Yes | Conversation messages. Content can be text or image/video content parts. |
| `max_completion_tokens` | integer | No | Maximum generated tokens, up to 65,536. |
| `temperature` | number | No | Sampling temperature in `[0, 2)`. Set only one of `temperature` and `top_p`. |
| `top_p` | number | No | Nucleus sampling probability in `(0, 1]`. Set only one of `temperature` and `top_p`. |
| `stream` | boolean | No | Return SSE chunks instead of one complete response. Default: `false`. |
| `stream_options` | object | No | Streaming options. `include_usage` defaults to `false`; set it to `true` to include usage in the final chunk. |
| `stop` | array | No | Array of stop sequences. The string form is not supported by the current AnyFast endpoint. |
| `seed` | integer | No | Seed from `0` to `2^31 - 1` for more repeatable output. |
| `presence_penalty` | number | No | Repetition control from `-2` to `2`. |
| `frequency_penalty` | number | No | Frequency-based repetition control from `-2` to `2`. |
| `enable_thinking` | boolean | No | Reasoning control field. With the OpenAI SDK, pass it through `extra_body`. |
| `tools` | array | No | Application-defined functions or supported tools. |
| `tool_choice` | string or object | No | Controls whether the model may call tools or must call a selected function. |
| `response_format` | object | No | Structured output configuration, such as `{ "type": "json_object" }`. Use non-thinking mode when required. |
Open the interactive API reference for Qwen3.6-Plus.