Poe API

Qwen3.5-397B-A17B

The Qwen3.5 series 397B-A17B native vision-language model is based on a hybrid architecture design that integrates linear attention mechanisms with sparse Mixture-of-Experts (MoE), achieving higher inference efficiency. Across a variety of tasks—including language understanding, logical reasoning, code generation, agentic tasks, image understanding, video understanding, and graphical user interface (GUI) interaction—it demonstrates exceptional performance comparable to current top-tier frontier models. Possessing robust code generation and agentic capabilities, it exhibits strong generalization across various agent scenarios. File Support: Text, Markdown, Image, Video and PDF files Context window: 262k tokens Optional parameters: Enable thinking about the response before giving a final answer: toggle it `on`, otherwise it is `off` by default. Set temperature to control randomness in the response: Set number from 1 to 2. This is set to `0.7` by default. Lower values make the output more focused and deterministic. Set max output tokens: Set number from 1 to 64000. This is set to 64000 by default.

OFFICIAL

Build with Qwen3.5-397B-A17B using the Poe API

Start by creating an API key, for use with any bot on Poe:

Generate API key

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 = "qwen3.5-397b-a17b",
    messages = [{
      "role": "user",
      "content": "You have two coins that look identical. One is fair (50% heads, 50% tails) and the other is a trick coin that always lands on heads. You pick a coin at random, flip it once, and it comes up heads. What is the probability that you picked the trick coin?"
    }]
)

print(chat.choices[0].message.content)

See the full documentation for comprehensive guidance on getting started.