Qwen3.5-397B-A17B
qwen/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.
Features
Serverless API
Docs
qwen/qwen3.5-397b-a17b is available via Novita's serverless API, where you pay per token. There are several ways to call the API, including OpenAI-compatible endpoints with exceptional reasoning performance.
Available Serverless
Run queries immediately, pay only for usage
Input$0.6 / M Tokens
Output$3.6 / M Tokens
Use the following code examples to integrate with our API:
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="<Your API Key>",
5 base_url="https://api.novita.ai/openai"
6)
7
8response = client.chat.completions.create(
9 model="qwen/qwen3.5-397b-a17b",
10 messages=[
11 {"role": "system", "content": "You are a helpful assistant."},
12 {"role": "user", "content": "Hello, how are you?"}
13 ],
14 max_tokens=64000,
15 temperature=0.7
16)
17
18print(response.choices[0].message.content)Info
Provider
Qwen
Quantization
-
Supported Functionality
Context Length
262144
Max Output
64000
Serverless
Supported
Function Calling
Supported
Structured Output
Supported
Reasoning
Supported
Input Capabilities
text, image, video
Output Capabilities
text