Qwen3.8 Max is Alibaba's language model with a 1.0M context window and up to 128K output tokens, starting at $2.00 / 1M input and $6.00 / 1M output. A massive 2.4T-parameter MoE flagship LLM optimized for coding, knowledge work, and autonomous multi-day programming tasks with native visual understanding.
Specifications
Canonical IDalibaba-qwen3-8-max
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Providers
Context Window1.0M tokens
Max Output128K tokens
Input ModalitiesImage
Output ModalitiesText
Reasoning Effortsdefault
Release Date · 2 days ago

Capabilities

Input1/5
Text·
Image
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning
Adaptive Reasoning·
Function Calling
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Cache Write 5m
$ / 1M
Vercel AI Gateway logo
Vercel AI Gateway
alibaba/qwen3.8-max
$2.00$6.00$0.25$2.50

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Qwen3.8 Max1.0M$2.00$6.00Current
Qwen3.7 Max1.0M$1.48$4.42Available
Qwen3.6 Max Preview262K$1.03$6.16Available
Qwen3 Max Thinking262K$0.780$3.90Available
Qwen3 Max262K$0.780$3.90Available
Qwen3 Max Preview262K$1.20$6.00Available
Qwen Max31K$0.345$1.38Available
Qwen VL Max131K$0.800$3.20Available
Qwen3 Max ThinkingAvailable
Qwen2.5 MaxAvailable
Qwen3 7 Max Preview$2.50$7.50Available

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
Qwen Audio 3 Flash RealtimeFlash$0.413$4.13
Qwen Audio 3 Plus RealtimePlus$0.688$5.50
Qwen Audio 3 Plus TTSPlus
EAGLE Qwen 2.5 3B Instruct
Qwen3.7 PlusPlus1.0M$0.320$1.28
Qwen3.6 27B262K$0.150$0.500
Qwen3.6 35B A3B262K$0.140$0.450
Qwen3.6 PlusPlus1.0M$0.325$1.95
Qwen Plus ThinkingPlus1.0M$0.400$1.20
Qwen3 235B A22B Instruct 2507262K$0.220$0.880

Model IDs

alibaba-qwen3-8-max
alibaba/qwen3.8-max
qwen/qwen3.8-max