Qwen
Qwen3.8 Max
qwen/qwen3.8-max-0902
An updated snapshot of Qwen3.8 Max from Alibaba's Qwen team: a 2.4-trillion-parameter mixture-of-experts model that takes text, image, and video input and returns text.
RoleThe big multimodal reasoner
$2
In / M
$6
Out / M
1.0M
Context
- AA intelligence index
- 33.7
- Inputs
- text, image, video
- Outputs
- text
- Tools
- Listed
- Structured output
- Listed
- Reasoning
- Listed
- Weights
- Not verified
- Listed
- Sep 3, 2026
01 · What it's good at
Use it for this.
Three jobs this model is built for, and the ones to give to something else.
01
Reasoning over images and video
02
Long inputs with a 1M-token context
03
A second frontier vendor for multimodal work
Skip it for
- Simple turns at default settings. The listing's default effort is xhigh
02 · Example tasks
What you'd actually send it.
Real inputs, not a benchmark. Paste one into the snippet below to try it.
You send
Here is a screenshot of our revenue dashboard. What changed this month, and what would you check next?
Why this model
Image input plus reasoning.
03 · Your stack
Where it sits: Plan & reason.
A reasoning step for media-heavy work, or a second frontier vendor in a multi-model setup.
Layer 01
Retrieve
Layer 02 · this model
Plan & reason
Layer 03
Do the volume
Layer 04
Gate & route
Layer 05
Draw, speak, listen
04 · Wire it up
One request. Paste and run.
Uses OpenRouter, so one key works for every model on this site. Set OPENROUTER_API_KEY and swap the prompt for one of the tasks above.
// OpenRouter speaks the OpenAI Chat Completions format.
const res = await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "qwen/qwen3.8-max-0902",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What changed on this dashboard this month?"
},
{
"type": "image_url",
"image_url": {
"url": "https://example.com/dashboard.png"
}
}
]
}
],
"reasoning": {
"effort": "low"
}
}),
});
const data = await res.json();
console.log(data.choices[0].message.content);
05 · Watch out for
Gotchas.
Default effort is xhigh, which is expensive for easy requests. Try low first.
Dated snapshot ids (-0902) keep behavior stable.
Sources
Lessons are written from each model's listing and the linked docs. We don't publish our own benchmark numbers; the index above is Artificial Analysis, as shown on OpenRouter.
Keep learning