Qwen3.5-Plus is a state-of-the-art multimodal model featuring a hybrid architecture designed for efficient deep thinking and robust visual understanding. It supports text, image, and video inputs within a massive 1M token context window, delivering performance comparable to leading global models across diverse tasks.
This model is served by Alibaba Cloud Int. from Singapore.
Notes:
- Context Window: 1,000,000
Parameter controls available:
1. Model
- Thinking to let the model reason step-by-step before answering. It is `on` by default.
- High resolution images to use max resolution for input images. It is `on` by default.
- Set Max Pixel count per image (default 2621440). This option is available only when high resolution is toggled `off`
2. Tools
- Web search to search the web for real-time info. It is `on` by default
- Web extractor to extract/read content from URLs. It is `on` by default
- Code interpreter to run Python code in a sandbox (requires thinking enabled). It is `on` by default
- Text-to-Image search to search web for images by text. It is `on` by default
- Image-to-Image search to find similar images from an uploaded image. It is `on` by default
3. Video
- Video FPS to extract frames per per second from video. (default 2.0, step 0.5)
- Treat multiple images as video to combine 4+ images into a video sequence. It is `off` by default.
Powered by a server managed by @empiriolabsai. Learn more
Build with Qwen3.5-Plus using the Poe API
Start by creating an API key, for use with any bot on Poe:
Code samples
python
import openai
client = openai.OpenAI(
api_key = "YOUR_POE_API_KEY", # or os.getenv("POE_API_KEY")
base_url = "https://api.poe.com/v1",
)
chat = client.chat.completions.create(
model = "qwen3.5-plus",
messages = [{
"role": "user",
"content": "How many r's are in the word 'strawberry'?"
}]
)
print(chat.choices[0].message.content)See the full documentation for comprehensive guidance on getting started.