Qwen3.8-Max

by Alibaba

Released 63 days after Qwen3.7-Plus · All Alibaba releases

Qwen3.8-Max is the most capable model in Alibaba's Qwen family to date, previewed at the World AI Conference in July 2026 and made generally available that August. It is a mixture-of-experts design with 2.4 trillion total parameters and roughly 95 billion active per token, accepting text, image, and video input with a hybrid thinking mode that can reason step by step or answer directly. Frontier-scale reasoning meets a context window approaching one million tokens and output up to 131K tokens, alongside native tool calling and structured output. The model suits long-document analysis, multimodal agent pipelines, and demanding coding or research tasks where a single request needs to hold an entire corpus in view.

Key info

Input
Output
Features
Context window
984K
Max output
131K
Input price
$2.00 /1M
Output price
$6.00 /1M
Released
  • US residency available
  • Zero data retention on pay-as-you-go
  • No training by default
  • GDPR DPA available

Available routes

Qwen3.8-Max runs on 5 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.

ProviderRegionZero data retentionTrainingInputOutput
MultiNo$2.00$6.00
USNo$1.65$4.95
USNo$2.00$6.00
MultiNo$2.00$6.00
USNo$2.00$6.00

Uptime and availability

Qwen3.8-Max runs on 4 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.

100%effective uptime, last 30 days
Averaged across these routes on their own, a single provider reached 100% over the same window.
Daily status through the gateway, which serves each request from whichever route is healthy.
4 monitored providers serve Qwen3.8-Max.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 1 further route for this model is not on the board yet and is not counted above. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Qwen3.8-Max has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Alibaba Cloud Multi-region

Zero data retention is not on by default — abuse monitoring. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention
Not by default — abuse monitoring. Derived from the logging, moderation and training facts.
Training
No training on customer data.
Logging
Abuse monitoring
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
GDPR DPA
DPA available
Transfer mechanism
SCCs

DeepInfra United States🇺🇸

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; unknown; DPA available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging, moderation and training facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
GDPR DPA
DPA available
Transfer mechanism
unknown

DigitalOcean United States🇺🇸

Zero data retention is not on by default — a moderation hold applies. No training on customer data. US; dpf sccs; DPA available.

Zero data retention
Not by default — a moderation hold applies. Derived from the logging, moderation and training facts.
Training
No training on customer data.
Logging
None
Moderation
Always on, holds flagged content
Caching
Content cached for replay
Subprocessor access
No subprocessor reads content
GDPR DPA
DPA available
Transfer mechanism
dpf sccs

Fireworks Multi-region

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging, moderation and training facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
Subprocessors may read content
GDPR DPA
DPA available
Transfer mechanism
SCCs

Novita United States🇺🇸

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; SCCs; DPA available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging, moderation and training facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
GDPR DPA
DPA available
Transfer mechanism
SCCs

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#31 of 641 LLMs
TierStrong
Output speed43 tok/s
First token1.69s
Intelligence Index40.3
Coding Index71.8
Reasoning & knowledge
GPQA Diamond
93%
Humanity's Last Exam
43%
Long-context reasoning
78%
Coding
SciCode
53%

Get started

Call Qwen3.8-Max through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "alibaba:global/qwen3.8-max",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Compare Qwen3.8-Max with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Alibaba

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation