Qwen: Qwen3.8 Max
qwen/qwen3.8-max
10th smartest of 158ReasoningToolsJSONVision
Intelligence
53.4
10th of 158
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$2.00
244th cheapest
Context
1M
131K max out
How it compares
Smarter than94%
of all ranked models
Cheaper than20%
of all ranked models
Overview
Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis97th percentile
Intelligence Index
53.4
Coding Index
68.9
GPQA Diamond
92%
Humanity's Last Exam
40%
SciCode
45%
Providers & pricing (1)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Alibaba | $2.00 | $6.00 | 1M | 100% |
Specifications
Context window1M
Max output131K
Knowledge cutoff—
Input modalitiestext, image, video
Output modalitiestext
Prompt caching—
Cache read price$0.250/M
ModeratedNo
Qwen3.8 Max FAQ
How much does Qwen3.8 Max cost?
Qwen3.8 Max costs $2.00 per million input tokens and $6.00 per million output tokens via OpenRouter, making it 244th cheapest of 305 paid models.
How smart is Qwen3.8 Max?
Qwen3.8 Max scores 53.4 on the Artificial Analysis Intelligence Index, ranking 10th of 158 benchmarked models, with a GPQA Diamond score of 92%.
What is Qwen3.8 Max's context window?
Qwen3.8 Max supports a 1M-token context window and can output up to 131K tokens. It accepts text, image, video input.