Alibaba: Qwen3 Max Preview

Flagship Qwen model for complex reasoning, coding, and agentic workflows

Model lab: Alibaba
Model family: qwen

Modalitiestext → text

Context window262,144

Maximum output32,768

Input · Context ≤ 256000 tokens · Maximum output 65536 tokensUSD 0.864 / 1M tokens

Output · Context ≤ 256000 tokens · Maximum output 65536 tokensUSD 3.84 / 1M tokens

Try now View docs

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/alibaba-cloud/qwen3-max-preview.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/alibaba-cloud/qwen3-max-preview"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Qwen3 Max Preview API Pricing

Type	Price information
Input · Context ≤ 256000 tokens · Maximum output 65536 tokens	USD 0.864 / 1M tokens
Output · Context ≤ 256000 tokens · Maximum output 65536 tokens	USD 3.84 / 1M tokens

Benchmarks

Intelligence Index · v4.312.6

Coding Index—

Agentic Index—

Performance

Performance trends

Throughput92.5 tok/sCurrent

Time to first token1.5 sCurrent

End-to-end latency8.0 sCurrent

Throughput

Current92.5 tok/s

Window average88.4 tok/s

Time to first token

Current1.5 s

Window average1.4 s

End-to-end latency

Current8.0 s

Window average7.5 s

Tail latency (P99)

Current17.7 s

Window average16.9 s

Prompt cache hit rate

Current26.4%

Window average24.3%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Qwen3 Max Preview Compare models

Model	Input price	Output price	Context window	Capabilities
Qwen3 Max PreviewThis page	USD 0.864 / 1M tokens · Context ≤ 256000 tokens · Maximum output 65536 tokens	USD 3.84 / 1M tokens · Context ≤ 256000 tokens · Maximum output 65536 tokens	262,144	Text output · Tool calling
Qwen3.8 2.4T A95B	USD 1.56 / 1M tokens	USD 4.56 / 1M tokens	262,144	Text output · Reasoning · Tool calling
Qwen3.7 Max	USD 0.66 / 1M tokens	USD 1.9804 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
Qwen3.6 Max Preview	USD 1.72 / 1M tokens	USD 10.288 / 1M tokens	262,144	Text output · Reasoning · Tool calling
Qwen3 Coder Next	USD 0.0864 / 1M tokens	USD 0.54 / 1M tokens	262,144	Text output · Tool calling

Model specifications

Input: text
Output: text
Context window: 262,144
Maximum output: 32,768
Release date: 2025-09-05
Attachments: No
Reasoning: No
Tool calling: Yes
Temperature setting: Yes
Open weights: No

Frequently asked questions

What is Qwen3 Max Preview for?

Flagship Qwen model for complex reasoning, coding, and agentic workflows

What inputs and outputs does Qwen3 Max Preview support?

Recorded inputs: text; outputs: text.

How is Qwen3 Max Preview priced?

The pricing table shows the current recorded Moduck price. For example: Input · Context ≤ 256000 tokens · Maximum output 65536 tokens USD 0.864 / 1M tokens; Output · Context ≤ 256000 tokens · Maximum output 65536 tokens USD 3.84 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Qwen3 Max Preview?

Current model records list Context window 262,144 tokens; Maximum output 32,768 tokens.

What model parameter does the Quickstart use?

The example uses moduck/alibaba-cloud/qwen3-max-preview. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.