Roar AI
DiscordGet started
All models
Alibaba · Open weights

Qwen 3.8 Max

Qwen 3.8 Max costs $2.21 per million input tokens and $6.63 per million output tokens on Roar AI. Alibaba’s flagship, and the first Max-tier Qwen with downloadable weights.

Input$2.21per 1M tokens
Output$6.63per 1M tokens
Context window1Mtokens

Qwen 3.8 Max API pricing

Input$2.21 per 1M tokens
Output$6.63 per 1M tokens
Cached input$0.2925 per 1M tokens
Cache write$3.25 per 1M tokens

Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost $13.26. Every rate is published and stays the same from one request to the next. See every model.

Rates as of 20 November 2026.

Specs

Made byAlibaba
ReleasedAugust 2026
TypeChat
Context window1M tokens
Longest answer131K tokens
ReadsText, images, video
Thinks before answeringYes, adjustable
WeightsOpen (Qwen3.8-Max License)
Size2.4T total, 95B active
Processed inSingapore
Model idqwen3.8-max

About Qwen 3.8 Max

Qwen 3.8 Max is Alibaba’s top model and the first Max-class Qwen whose weights you can download: a 2.4-trillion-parameter mixture of experts. Alibaba trained it to check its own visual output, and reports 67.7% on SWE-bench Pro, 92.6% on GPQA Diamond and 86.1% on the OSWorld computer-use test.

Through the API it reads images and video and holds a million tokens; the downloadable version is text-only with a shorter context. It thinks before answering, at three effort levels.

What is Qwen 3.8 Max good for?

  • Frontier-level coding agents.
  • Operating desktop software.
  • Research and analysis across long documents.

Qwen 3.8 Max limitations

  • Every headline score is from Alibaba’s internal runs.
  • The licence on the open weights restricts very large AI-service companies.

How to use the Qwen 3.8 Max API

Use the OpenAI SDK you already have: point it at Roar AI and set the model name. Read the docs.

from openai import OpenAI

client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")

reply = client.chat.completions.create(
    model="qwen3.8-max",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

Qwen 3.8 Max FAQ

How much does Qwen 3.8 Max cost?

Input is $2.21 per 1M tokens; output is $6.63 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost $13.26.

Can I use Qwen 3.8 Max alongside other models?

Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from Qwen 3.8 Max to another model only means changing the model name in your code.

Is Qwen 3.8 Max open source?

Its weights are open under the Qwen3.8-Max License licence, so you could run it yourself. Through Roar AI you call it like any other model, with no servers to manage.

What is the context window of Qwen 3.8 Max?

Qwen 3.8 Max can read up to 1M tokens in one request, and write an answer of up to 131K tokens.

Can Qwen 3.8 Max read images and PDFs?

It reads images directly. You can still send it a PDF: Roar AI turns each page into text first, at no extra charge.

Start using Qwen 3.8 Max

Create a free account, get an API key and call Qwen 3.8 Max with the OpenAI SDK.