Qwen

Qwen3.8 Max

CTX1M

93Quality

Reasoning · Vision · Tools

Input$2/M

Output$6/M

2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows

PaidProprietary961/1040

Drag to turn

QwenTextUncommon

Qwen3.8 Max

2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows

qwen3.8-max

Type: Text
Quality: 93 · Top 7% on the Epoch Capabilities Index
Context window: 1,000,000 tokens
Max output: 131,072 tokens
Input price: $2.00 / 1M tokens
Output price: $6.00 / 1M tokens
Cache read: $0.25 / 1M tokens
Cache write: $2.50 / 1M tokens
Released: Aug 3, 2026
Knowledge cutoff: —
Takes in: Text, Image, Video, PDF
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
File attachments: Yes
Access: Paid
License: Proprietary
Rarity: Uncommon
Set number: 961/1040

Open Qwen docs Quality 93 Where to run it 38 Evolution 5/5 Meet its creature Battle Grok 4.7

Weights aren’t public. Use is governed by Qwen’s terms. Specs from models.dev, last changed Oct 18, 2026. Official source: www.alibabacloud.com.

How good is it?

Public leaderboard scores for Qwen3.8 Max, refreshed daily from Epoch AI and LMArena.

Top 7% of the 277 models on the Epoch Capabilities Index: #20.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Epoch Capabilities Index#20 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.156.9 index
LMArena Text#17 of 416
People compare two anonymous answers and vote for the better one.1,483 rating
LMArena Text · Coding#23 of 411
The text arena’s coding prompts only.1,502 rating
LMArena Text · Math#14 of 400
The text arena’s math prompts only.1,502 rating
LMArena Text · Creative writing#16 of 414
The text arena’s creative writing prompts only.1,479 rating
LMArena WebDev#11 of 144
Each model builds a web app from the same prompt; people pick the better one.1,672 rating
LMArena Vision#9 of 165
Questions about images, voted by people.1,314 rating

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

38 providers sell Qwen3.8 Max through an API. Prices are per million tokens, cheapest first.

CheapestDevPass (LLM Gateway)$1.54 in · $4.63 out
Free to try4 providersAlibaba Token Plan, Alibaba Token Plan (China), Kenari, …
From the labAlibaba$2.00 in · $6.00 out

API providers

Provider	Input	Output	Context
Alibaba Token PlanFree`qwen3.8-max`	Free	Free	1M
Alibaba Token Plan (China)Free`qwen3.8-max`	Free	Free	1M
KenariFree`qwen3-8-max`	Free	Free	1M
SCNet Token PlanFree`Qwen3.8-Max`	Free	Free	1M
DevPass (LLM Gateway)Cheapest paid`qwen3.8-max`	$1.54	$4.63	1M
LLM Gateway`scx-ai-gp/qwen3.8-max`	$1.54	$4.63	1M
Vancine`qwen3.8-max`	$1.60	$4.80	1M
Deep Infra`Qwen/Qwen3.8-Max`	$1.65	$4.95	256K
AIHubMix`qwen3.8-max`	$1.69	$5.07	991K
Ofox`qwen/qwen3.8-max`	$1.71	$5.14	1M

Show 28 more providers

Provider	Input	Output	Context
Alibaba (China)`qwen3.8-max`	$1.78	$5.33	1M
SCX.ai`Qwen3.8-Max`	$1.81	$5.45	1M
CrossModel`qwen/qwen3.8-max`	$1.88	$5.63	1M
Abacus`qwen3.8-max`	$2.00	$6.00	1M
AlibabaOfficial`qwen3.8-max`	$2.00	$6.00	1M
Charm Hyper`qwen3.8-max`	$2.00	$6.00	1M
ClinePass`cline-pass/qwen3.8-max`	$2.00	$6.00	1M
Cloudflare AI Gateway`alibaba/qwen3.8-max`	$2.00	$6.00	1M
CommandCode`Qwen/Qwen3.8-Max`	$2.00	$6.00	1M
DigitalOcean`qwen3.8-max`	$2.00	$6.00	1M
Eden AI`qwen/qwen3.8-max`	$2.00	$6.00	1M
EmpirioLabs AI`qwen3-8-max`	$2.00	$6.00	1M
Fireworks AI`accounts/fireworks/models/qwen3p8-max`	$2.00	$6.00	262K
GMI Cloud`Qwen/Qwen3.8-Max`	$2.00	$6.00	262K
Merge Gateway`qwen/qwen3.8-max`	$2.00	$6.00	1M
Modal`Qwen/Qwen3.8-2.4T-A95B`	$2.00	$6.00	1.01M
NanoGPT`qwen/qwen3.8-max`	$2.00	$6.00	991K
Novita AI`qwen/qwen3.8-max`	$2.00	$6.00	1M
OpenCode`qwen3.8-max`	$2.00	$6.00	262K
OpenCode Go`qwen3.8-max`	$2.00	$6.00	1M
Opper`qwen3.8-max`	$2.00	$6.00	984K
OrcaRouter`qwen/qwen3.8-max`	$2.00	$6.00	1M
Requesty`qwen3.8-max`	$2.00	$6.00	1.05M
Vercel AI Gateway`alibaba/qwen3.8-max`	$2.00	$6.00	262K
302.AI`qwen3.8-max`	$2.16	$6.36	1M
above.dev`qwen3.8-max`	$2.20	$6.60	1M
Venice AI`qwen-3-8-max`	$2.50	$7.50	1M
AI/ML API`alibaba/qwen3.8-max`	$2.60	$7.80	1M

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.

Qwen3.8 Max

Qwen3.8 Max

How good is it?

Leaderboards

Where to run it

API providers

Face off

More from Qwen

Qwen-Image-2.1-Turbo

Qwen3.8 Omni Flash

Qwen-Image-2.1

Qwen3.8 Flash

Qwen3.8-Flash-Next

Qwen3.8-2.4T-A95B

Qwen3.8-27B

Qwen3.7 Flash