Qwen3 Max Preview
Qwen logo

Qwen3 Max Preview

qwen3-max-preview
Qwen
The latest qwen3-max-preview model is the preview version of the Qwen3 series Max model. Compared to the Qwen 2.5 series, it features significant improvements in overall general capabilities, including enhanced bilingual (Chinese and English) text comprehension, complex instruction following, subjective open-task performance, multilingual abilities, and tool usage. Additionally, the model exhibits reduced knowledge hallucination.

Pricing

TierPricingCache Read
Input<=32K
$0.8219$3.2877
-
32K<Input<=128K
$1.3699$5.4795
-
128K<Input<=2520K
$2.0548$8.2192
-

Input Modalities

  • Text
  • Vision

Output Modalities

  • Text

Capabilities

  • Tools
  • Tool calling
  • Structured outputs

Providers

Alibaba Cloud qwen3-max-preview
Pricing$0.8219$3.2877
Pricing$1.3699$5.4795
Pricing$2.0548$8.2192
Context0
Max output0
Latency-
Throughput-
Uptime
0.00% uptime 2 days ago
0.00% uptime yesterday
0.00% uptime today

Performance for qwen3-max-preview

Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).

Uptime
Loading...
Latency
Loading...
Throughput
Loading...

Try this model

Python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://shkq.org/v1",
)

response = client.chat.completions.create(
    model="qwen3-max-preview",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

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

Frequently asked questions

What is Qwen3 Max Preview?

The latest qwen3-max-preview model is the preview version of the Qwen3 series Max model. Compared to the Qwen 2.5 series, it features significant improvements in overall general capabilities, including enhanced bilingual (Chinese and English) text comprehension, complex instruction following, subjective open-task performance, multilingual abilities, and tool usage. Additionally, the model exhibits reduced knowledge hallucination.