Qwen3.8 Max
qwen/qwen3.8-max
A 2.4T-parameter MoE flagship for coding and knowledge work. Programs autonomously for days to deliver complete projects end to end, with native visual understanding across planning, execution, and verification, plus deep semantic analysis of ultra-long documents and video.
Price
| Input | $2/百万 tokens |
| Cached reads | $0.25/百万 tokens |
| Output | $6/百万 tokens |
Use the following code example to integrate our API:
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="<Your API Key>",
5 base_url="https://api.highwayapi.ai/openai"
6)
7
8response = client.chat.completions.create(
9 model="qwen/qwen3.8-max",
10 messages=[
11 {"role": "system", "content": "You are a helpful assistant."},
12 {"role": "user", "content": "Hello, how are you?"}
13 ],
14 max_tokens=131702,
15 temperature=0.7
16)
17
18print(response.choices[0].message.content)Information
Provider
Quantization
-
Supported Features
Context Length
1M
Maximum Output
131.7K
serverless
Supported
推理
Supported
结构化输出
Supported
函数调用
Supported
Input Capabilities
text, image, video
Output Capabilities
text